© 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. 10-RES-JB
    11. 11062
    Prev
    Next
    INDEX
    Explanations

    timestamps

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and timestamps associated with events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.74
    .","
    -0.70
     bonded
    -0.68
     cle
    -0.64
    kef
    -0.63
    rop
    -0.62
     fert
    -0.62
    ``
    -0.62
    assets
    -0.62
    achus
    -0.61
    POSITIVE LOGITS
    jamin
    0.93
    resa
    0.81
    Marginal
    0.80
    arnaev
    0.76
    ertodd
    0.72
    stanbul
    0.72
    ercise
    0.69
    dinand
    0.68
    ********************************
    0.66
    ULE
    0.65
    Activations Density 0.120%

    No Known Activations