© 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. 9-RES-JB
    11. 14836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating absence or lack

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of relevance or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gression
    -0.81
    gee
    -0.69
    fs
    -0.68
    nm
    -0.68
    batch
    -0.67
    nee
    -0.65
    ioxide
    -0.64
    ritz
    -0.64
    ford
    -0.63
    ffe
    -0.63
    POSITIVE LOGITS
     resembling
    0.97
     else
    0.79
     recourse
    0.75
     towed
    0.71
     redeem
    0.67
     qual
    0.67
     constructive
    0.65
     precon
    0.64
    ĸļ
    0.64
     bearing
    0.63
    Activations Density 0.050%

    No Known Activations