© 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. 4934
    Prev
    Next
    INDEX
    Explanations

    specific references to events, places, and people

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" used repeatedly 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
    ratulations
    -0.76
    LOG
    -0.72
    scape
    -0.70
    loads
    -0.66
    thia
    -0.62
    yet
    -0.62
    selling
    -0.62
    gans
    -0.61
    umeric
    -0.61
    opsis
    -0.61
    POSITIVE LOGITS
     behest
    1.40
     outset
    1.32
     forefront
    1.13
     expense
    1.11
     helm
    1.09
     end
    0.96
     intersection
    0.95
     discretion
    0.94
     same
    0.93
     intersections
    0.92
    Activations Density 0.148%

    No Known Activations