© 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. 18732
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of items or concepts that are miniaturized

    oai_token-act-pair · gpt-3.5-turbo

    references to miniature or small-scale items and concepts

    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
    Ö¼
    -0.77
    âķIJâķIJ
    -0.72
    IAL
    -0.71
     defe
    -0.68
    REAM
    -0.65
    mingham
    -0.65
     neutrality
    -0.60
    xual
    -0.60
     forcefully
    -0.60
    enance
    -0.59
    POSITIVE LOGITS
    ature
    1.57
    atur
    1.42
    atures
    1.27
    eco
    0.84
    ota
    0.84
    ocular
    0.84
    atomic
    0.81
     sized
    0.81
    osh
    0.74
    oby
    0.73
    Activations Density 0.022%

    No Known Activations