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

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 5014
    Prev
    Next
    INDEX
    Explanations

    geographic locations and historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    496
    +0.10
    0.5%
    134
    +0.10
    0.5%
    209
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.14
    284
    +0.10
    0.14
    701
    +0.10
    0.10
    Negative Logits
    DERR
    -0.67
     mascul
    -0.59
    «ĺ
    -0.58
    WARE
    -0.57
     brood
    -0.56
     suites
    -0.56
     reversible
    -0.54
    ¿½
    -0.53
     persu
    -0.52
     fet
    -0.52
    POSITIVE LOGITS
    uru
    0.90
    oy
    0.87
    icz
    0.85
    iy
    0.84
    uy
    0.80
    aru
    0.79
    igs
    0.78
    anes
    0.78
    utsu
    0.77
    und
    0.76
    Activations Density 6.063%

    No Known Activations