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

    Neuronpedia

    APICircuit 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. 45408
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and events

    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
    +0.21
    1.0%
    514
    +0.10
    0.5%
    446
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.21
    -0.04
    665
    +0.10
    0.16
    59
    +0.10
    0.08
    Negative Logits
    aic
    -0.75
    mong
    -0.72
    eway
    -0.66
    acies
    -0.64
    avery
    -0.61
    itect
    -0.60
    ¶ħ
    -0.60
    ternally
    -0.59
    aina
    -0.59
    icons
    -0.59
    POSITIVE LOGITS
     abruptly
    0.64
     last
    0.64
     Leopard
    0.60
     unexpectedly
    0.57
    stad
    0.56
    ipeg
    0.55
     nineteen
    0.55
     withd
    0.55
     fateful
    0.54
     LAST
    0.54
    Activations Density 9.538%

    No Known Activations