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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45730
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences, emotional reflections, and viewpoints

    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
    534
    +0.09
    0.6%
    512
    +0.07
    0.4%
    707
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    564
    +0.09
    0.09
    534
    +0.07
    0.05
    284
    +0.07
    0.07
    Negative Logits
    ongo
    -0.53
    arb
    -0.52
    iden
    -0.51
    ylan
    -0.49
    eri
    -0.49
    outh
    -0.47
    isin
    -0.45
    atto
    -0.44
    igh
    -0.44
    isc
    -0.43
    POSITIVE LOGITS
    soever
    0.62
    lier
    0.53
     THEY
    0.53
     Saud
    0.49
    liest
    0.48
     disple
    0.48
     prevailed
    0.48
    isSpecialOrderable
    0.48
     dictated
    0.47
     desired
    0.46
    Activations Density 5.470%

    No Known Activations