© 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. 3149
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of hope

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hops in relation to brewing or beer

    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
     payable
    -0.72
    ateral
    -0.68
    anguage
    -0.65
    $$$$
    -0.61
     behold
    -0.60
     gou
    -0.59
     Frankenstein
    -0.58
     ..........
    -0.58
    ude
    -0.57
     Barbara
    -0.57
    POSITIVE LOGITS
    eful
    1.48
    efully
    1.43
    eless
    1.24
    Hop
    1.10
    emaker
    1.01
    lite
    0.93
    retty
    0.90
    fen
    0.88
    sticks
    0.88
    olitics
    0.87
    Activations Density 0.034%

    No Known Activations