© 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. 4941
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to technological terms or software

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the G20 Summit and related events

    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
    ĸļ
    -0.69
     enactment
    -0.68
     scrut
    -0.67
     Lowell
    -0.66
    ĪĴ
    -0.65
    ACTED
    -0.64
     exception
    -0.63
     writ
    -0.61
     consistency
    -0.59
     caucuses
    -0.58
    POSITIVE LOGITS
    raltar
    1.02
    apon
    0.95
    onz
    0.91
    vernment
    0.90
    apons
    0.88
    ierrez
    0.87
    estone
    0.85
    agall
    0.85
    veland
    0.82
    protein
    0.81
    Activations Density 0.082%

    No Known Activations