© 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. 22516
    Prev
    Next
    INDEX
    Explanations

    locations or geographical information

    oai_token-act-pair · gpt-3.5-turbo

    commas and phrases indicating lists or additional information

    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
    iral
    -0.75
    thood
    -0.71
    obin
    -0.68
    hetical
    -0.66
    isner
    -0.66
    isy
    -0.64
    viation
    -0.63
    act
    -0.62
    SON
    -0.62
    Async
    -0.62
    POSITIVE LOGITS
     where
    1.40
     located
    1.23
     whence
    1.19
    where
    1.17
     situated
    1.16
     adjoining
    1.14
     adjacent
    1.11
     overlooking
    1.06
     southwest
    1.03
     bordering
    1.02
    Activations Density 0.395%

    No Known Activations