© 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. 34707
    Prev
    Next
    INDEX
    Explanations

    phrases related to journalism, actions, and subscription offers

    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
    101
    +0.13
    0.6%
    120
    +0.10
    0.4%
    29
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.13
    0.08
    731
    +0.10
    0.05
    503
    +0.10
    0.06
    Negative Logits
     [+
    -0.71
    illes
    -0.67
    rehens
    -0.67
     Hut
    -0.63
     Mole
    -0.62
    -------
    -0.62
    idas
    -0.61
    agi
    -0.61
    tons
    -0.60
     cel
    -0.60
    POSITIVE LOGITS
    soType
    0.72
    eem
    0.67
    govtrack
    0.66
    éļ
    0.62
    venant
    0.62
    yright
    0.62
    APD
    0.61
    DonaldTrump
    0.60
     Lyft
    0.59
    VK
    0.59
    Activations Density 3.075%

    No Known Activations