© 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. 6163
    Prev
    Next
    INDEX
    Explanations

    year ranges or specific years indicated in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses in text

    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
     retard
    -0.81
     entitle
    -0.72
    emonic
    -0.70
     wre
    -0.66
     hazards
    -0.66
     incarn
    -0.65
     everyday
    -0.65
     spatial
    -0.65
     tenants
    -0.64
     rog
    -0.64
    POSITIVE LOGITS
    formerly
    1.44
    which
    1.42
    whose
    1.38
    who
    1.34
    although
    1.29
    where
    1.29
    pictured
    1.27
    excluding
    1.19
    via
    1.18
    albeit
    1.16
    Activations Density 0.147%

    No Known Activations