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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 45540
    Prev
    Next
    INDEX
    Explanations

    phrases related to collecting items in a game

    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
    436
    +0.05
    0.5%
    727
    +0.05
    0.5%
    447
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    739
    +0.05
    0.07
    640
    +0.05
    0.20
    727
    +0.05
    0.06
    Negative Logits
    swer
    -0.49
    estamp
    -0.42
     nodd
    -0.41
    sembly
    -0.39
    hett
    -0.39
    ittal
    -0.38
    ancial
    -0.38
    tsky
    -0.38
    etheless
    -0.37
    ieth
    -0.37
    POSITIVE LOGITS
    Weapon
    0.41
     Mana
    0.41
     Defeat
    0.39
     Healing
    0.39
     Piercing
    0.38
    Increases
    0.38
     Increases
    0.38
     Meditation
    0.36
     cooldown
    0.36
    Charges
    0.35
    Activations Density 7.421%

    No Known Activations