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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19185
    Prev
    Next
    INDEX
    Explanations

    words related to fuel and energy sources

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with hydrocarbons and biofuels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    claw
    -0.67
    displayText
    -0.65
     traveller
    -0.65
    felt
    -0.64
     distinguishing
    -0.64
     omission
    -0.63
    FIX
    -0.62
     Cly
    -0.59
     Cheong
    -0.59
     base
    -0.58
    POSITIVE LOGITS
    rencies
    1.23
    acters
    0.98
    ansion
    0.91
    anic
    0.88
    puters
    0.87
    inery
    0.86
    vironments
    0.85
    puting
    0.84
    ilic
    0.84
    ineries
    0.83
    Activations Density 0.100%

    No Known Activations