© 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. 7-RES-JB
    11. 6421
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers relating to quantities or measurements, like "500" or "400"

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 500 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acia
    -0.77
    verend
    -0.75
    warts
    -0.72
     symmetry
    -0.71
    odynam
    -0.71
    asio
    -0.71
    swick
    -0.71
    udic
    -0.70
    ophon
    -0.69
    wered
    -0.68
    POSITIVE LOGITS
    px
    0.96
    Hz
    0.86
     MHz
    0.83
    Mbps
    0.82
     mL
    0.81
    0002
    0.80
     gallons
    0.80
     ml
    0.80
    ãĥ©ãĥ³
    0.79
    mA
    0.79
    Activations Density 0.032%

    No Known Activations