© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6178
    Prev
    Next
    INDEX
    Explanations

    fantasy creatures and objects in a gaming context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    76
    +0.10
    0.5%
    566
    +0.09
    0.4%
    593
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.10
    0.01
    548
    +0.09
    0.01
    583
    +0.09
    0.01
    Negative Logits
    rera
    -0.83
    terson
    -0.76
    osate
    -0.74
     misunder
    -0.67
    ouf
    -0.66
    uterte
    -0.65
    etts
    -0.65
    enegger
    -0.63
     notwithstanding
    -0.63
    orius
    -0.62
    POSITIVE LOGITS
     demons
    0.65
     vines
    0.65
    ################
    0.60
     Demonic
    0.60
     woodland
    0.58
     clouds
    0.58
     bushes
    0.58
    åĤ
    0.58
    orce
    0.57
     blink
    0.57
    Activations Density 0.014%

    No Known Activations