© 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. 10-RES-JB
    11. 7912
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing the importance of a fact or statement

    oai_token-act-pair · gpt-3.5-turbo

    statements that confirm or emphasize facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocation
    -0.67
    iencies
    -0.67
    LC
    -0.64
    tu
    -0.63
    rals
    -0.61
    ãĤ©
    -0.61
    ocrats
    -0.60
    erg
    -0.60
    ocracy
    -0.60
    igion
    -0.59
    POSITIVE LOGITS
     downright
    1.24
     quite
    0.98
     even
    0.97
     practically
    0.88
     almost
    0.87
     virtually
    0.85
     pretty
    0.84
     entire
    0.80
     worse
    0.77
     contrary
    0.77
    Activations Density 0.209%

    No Known Activations