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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45172
    Prev
    Next
    INDEX
    Explanations

    descriptive language pertaining to government policies and programs

    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
    +0.15
    1.2%
    459
    +0.09
    0.7%
    756
    +0.09
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.15
    -0.13
    756
    +0.09
    -0.28
    570
    +0.09
    -0.01
    Negative Logits
     Opp
    -0.34
     Hung
    -0.34
     Alger
    -0.33
    agos
    -0.33
    xia
    -0.31
     Mons
    -0.30
     Posted
    -0.30
    gor
    -0.29
     Burke
    -0.29
     Anthropology
    -0.29
    POSITIVE LOGITS
     accordingly
    0.66
     thereafter
    0.62
     thereof
    0.59
     thereto
    0.55
     therein
    0.55
    ).[
    0.45
     attRot
    0.44
     afterward
    0.44
     afterwards
    0.43
     versa
    0.38
    Activations Density 31.680%

    No Known Activations