© 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. 3077
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements, particularly percentages and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    statistical figures and percentages

    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
     Doodle
    -0.64
     Priority
    -0.61
     Ultr
    -0.61
    leep
    -0.61
     Protector
    -0.59
    nesday
    -0.59
     sandbox
    -0.59
     Immunity
    -0.58
     drafts
    -0.58
     kids
    -0.58
    POSITIVE LOGITS
     383
    0.75
    iah
    0.73
     189
    0.73
    indust
    0.72
     379
    0.70
     387
    0.70
     229
    0.70
     369
    0.69
     177
    0.68
     363
    0.68
    Activations Density 0.156%

    No Known Activations