© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20224
    Prev
    Next
    INDEX
    Explanations

    mentions of the number '40'

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 40 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vet
    -0.70
    theless
    -0.70
    creen
    -0.68
    isoft
    -0.67
     attendant
    -0.65
     stagnation
    -0.65
    onen
    -0.64
    leasing
    -0.62
    fecture
    -0.62
    veyard
    -0.61
    POSITIVE LOGITS
    nm
    0.86
    625
    0.83
    %
    0.83
    %-
    0.82
    dfx
    0.79
    00
    0.76
    345
    0.74
    acht
    0.72
    acers
    0.70
    40
    0.70
    Activations Density 0.077%

    No Known Activations