© 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. 6462
    Prev
    Next
    INDEX
    Explanations

    times written in a specific format, such as hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and numerical data related to events or actions

    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
    udeb
    -0.86
    ulet
    -0.75
     STATS
    -0.71
    lessly
    -0.69
    icipated
    -0.65
    respective
    -0.65
    spons
    -0.65
    iverpool
    -0.64
    asel
    -0.64
    esan
    -0.62
    POSITIVE LOGITS
    PM
    0.95
    AM
    0.91
    pm
    0.90
     pm
    0.86
     autop
    0.84
     PDT
    0.80
     PM
    0.70
    âĢ³
    0.69
    Interstitial
    0.68
     PST
    0.68
    Activations Density 0.037%

    No Known Activations