© 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. 5019
    Prev
    Next
    INDEX
    Explanations

    opinions, statistics, and facts related to various social and political issues

    oai_token-act-pair · gpt-3.5-turbo

    issues related to societal concerns and public opinion

    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
     legions
    -0.71
     batches
    -0.66
    IAS
    -0.65
    aris
    -0.63
    batch
    -0.63
     PCR
    -0.62
    esis
    -0.61
     Sass
    -0.59
     frantic
    -0.58
    igs
    -0.57
    POSITIVE LOGITS
     favorably
    0.79
     compared
    0.77
    uci
    0.76
     Helpful
    0.76
    _(
    0.73
     personally
    0.72
     unaff
    0.71
    aucas
    0.71
    avorable
    0.71
     negatively
    0.70
    Activations Density 0.396%

    No Known Activations