© 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. 13707
    Prev
    Next
    INDEX
    Explanations

    phrases related to education, research, and academic institutions

    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
    +0.23
    1.1%
    647
    +0.13
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.23
    0.08
    644
    +0.13
    0.11
    679
    +0.12
    0.17
    Negative Logits
    theless
    -0.99
    tnc
    -0.66
    taboola
    -0.66
     sled
    -0.65
     ages
    -0.64
    mere
    -0.63
     tame
    -0.63
    seys
    -0.63
    ...]
    -0.63
    DIT
    -0.62
    POSITIVE LOGITS
     Square
    0.73
    itute
    0.72
    una
    0.72
     Herz
    0.69
    ollah
    0.68
     Research
    0.65
     Transparency
    0.64
     Institute
    0.64
    Research
    0.63
    uity
    0.62
    Activations Density 9.049%

    No Known Activations