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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 34231
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings or administrative actions

    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
    +0.13
    0.6%
    481
    +0.12
    0.6%
    418
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.13
    0.20
    288
    +0.12
    0.26
    620
    +0.09
    0.04
    Negative Logits
    eng
    -0.70
    aping
    -0.63
    racted
    -0.62
    usted
    -0.61
    ENG
    -0.60
    agonist
    -0.60
    assemb
    -0.59
    cong
    -0.58
    entin
    -0.57
    uan
    -0.57
    POSITIVE LOGITS
     norms
    1.01
     requirements
    0.87
     sensibilities
    0.83
     expectations
    0.81
     norm
    0.81
     ideals
    0.80
     aspirations
    0.76
     standards
    0.76
     principles
    0.76
     guidelines
    0.76
    Activations Density 13.834%

    No Known Activations