Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45368
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and network communication

    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
    +0.10
    0.6%
    459
    +0.10
    0.6%
    288
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.10
    0.07
    649
    +0.10
    0.02
    202
    +0.09
    0.07
    Negative Logits
    ments
    -0.69
    ï¸
    -0.68
    ãĥĦ
    -0.63
    ¶ħ
    -0.62
    acters
    -0.60
    itism
    -0.60
    selves
    -0.59
    */(
    -0.57
    wich
    -0.57
    geons
    -0.55
    POSITIVE LOGITS
    trl
    0.93
    ALLY
    0.85
    ULAR
    0.84
    ENSE
    0.82
    entric
    0.82
    ANN
    0.81
    HAEL
    0.80
    ICLE
    0.77
    IJ
    0.74
    BM
    0.73
    Activations Density 6.386%

    No Known Activations