© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 13945
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of 'hit' in various contexts

    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
    110
    +0.03
    0.5%
    386
    +0.03
    0.5%
    643
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.03
    0.12
    326
    +0.03
    0.21
    232
    +0.03
    0.10
    Negative Logits
    utical
    -0.30
    女
    -0.25
    etheless
    -0.23
    ouver
    -0.22
    NetMessage
    -0.22
    ipation
    -0.21
    ¬¼
    -0.21
    IDE
    -0.20
    zzo
    -0.20
    ħĭ
    -0.20
    POSITIVE LOGITS
    chens
    0.42
    achi
    0.30
    rig
    0.23
    ring
    0.23
    ron
    0.23
    ronic
    0.23
    rat
    0.23
    rate
    0.23
    gear
    0.23
    gew
    0.22
    Activations Density 7.622%

    No Known Activations