© 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. 46012
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual believed to be a significant figure in the field of cryptocurrency

    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
    214
    +0.13
    0.7%
    356
    +0.13
    0.6%
    238
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.25
    556
    +0.13
    0.10
    308
    +0.11
    0.06
    Negative Logits
    oine
    -0.82
    eday
    -0.78
    ramid
    -0.74
    aeus
    -0.72
    gom
    -0.66
    uries
    -0.65
    roxy
    -0.65
    eteria
    -0.65
    alion
    -0.64
    enary
    -0.62
    POSITIVE LOGITS
    åĤ
    0.88
    voy
    0.77
    ption
    0.74
    qi
    0.71
    MENT
    0.71
    issance
    0.68
    liness
    0.65
    MENTS
    0.64
    izont
    0.64
    nings
    0.63
    Activations Density 10.192%

    No Known Activations