© 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. 40360
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations related to current events or news

    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
    447
    +0.09
    0.9%
    420
    +0.06
    0.6%
    61
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.09
    0.13
    61
    +0.06
    0.10
    603
    +0.05
    0.09
    Negative Logits
    urers
    -0.38
    ifferent
    -0.36
    seless
    -0.35
    antics
    -0.34
    urally
    -0.33
    efficiency
    -0.32
    arity
    -0.32
    efficient
    -0.31
    ocations
    -0.31
    ERG
    -0.31
    POSITIVE LOGITS
     grandson
    0.40
     nephew
    0.38
     wife
    0.37
     granddaughter
    0.37
     deceased
    0.36
     retiring
    0.36
    )]
    0.36
     ?)
    0.36
    wife
    0.35
     eldest
    0.35
    Activations Density 14.123%

    No Known Activations