© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of outcomes or consequences resulting from prior events or situations

    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
     Vaugh
    -0.70
    arag
    -0.66
    tera
    -0.66
    vae
    -0.65
    rones
    -0.65
    anus
    -0.64
    estern
    -0.64
    nan
    -0.61
    sites
    -0.60
    asca
    -0.60
    POSITIVE LOGITS
     thereof
    0.90
     of
    0.74
    ãĤ¯
    0.73
    forth
    0.66
    ,...
    0.65
    ainer
    0.61
    loss
    0.61
     CLSID
    0.60
    ãĥł
    0.58
    uary
    0.56
    Activations Density 0.017%

    No Known Activations