© 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. 3147
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and demographics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate analysis or discussion of social groups and their characteristics

    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
    hene
    -0.79
    ankind
    -0.69
    herent
    -0.67
    atre
    -0.67
    sburgh
    -0.66
    vernment
    -0.65
    hash
    -0.64
    raft
    -0.64
    tern
    -0.63
    aste
    -0.63
    POSITIVE LOGITS
     namely
    1.22
     albeit
    1.15
     whereby
    1.13
     although
    1.10
     which
    1.03
     including
    1.03
     notably
    1.03
     lest
    1.00
     wherein
    0.99
     suggesting
    0.99
    Activations Density 0.501%

    No Known Activations