© 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. 33118
    Prev
    Next
    INDEX
    Explanations

    JSON and HTML elements in a programming context

    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
    640
    +0.10
    0.5%
    612
    +0.10
    0.4%
    296
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.10
    0.04
    568
    +0.10
    0.03
    59
    +0.09
    0.03
    Negative Logits
     rom
    -0.71
    ixels
    -0.66
     uncond
    -0.65
     ste
    -0.65
     assemb
    -0.64
    esy
    -0.61
     Chao
    -0.60
    rogen
    -0.59
     Chong
    -0.58
     crypt
    -0.58
    POSITIVE LOGITS
    },{"
    1.09
    },"
    0.98
    ]}
    0.89
     "$:/
    0.86
    ricanes
    0.82
    quickShipAvailable
    0.81
    ../
    0.80
    arag
    0.79
    catentry
    0.79
    Sensor
    0.79
    Activations Density 1.939%

    No Known Activations