© 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. 22523
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a lack of interest or indifference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to interest or disinterest in various topics or activities

    oai_token-act-pair · gpt-3.5-turbo
    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
    byter
    -0.69
    hem
    -0.65
    ggles
    -0.65
    osen
    -0.61
     bearer
    -0.60
    orbit
    -0.60
     ascend
    -0.60
    opers
    -0.59
    ioxide
    -0.58
    ework
    -0.58
    POSITIVE LOGITS
    ately
    0.86
    ¬
    0.85
    inery
    0.78
    lessly
    0.72
    uates
    0.71
    ª
    0.69
    enza
    0.68
    ¿½
    0.68
    uated
    0.67
    ulous
    0.65
    Activations Density 0.079%

    No Known Activations