© 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. 21451
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Jones" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jones" in various contexts

    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
    ULAR
    -0.82
    aneously
    -0.80
    racted
    -0.78
    ptions
    -0.73
    rous
    -0.73
    utive
    -0.72
    ulatory
    -0.71
    aneous
    -0.71
    ancies
    -0.69
    ories
    -0.68
    POSITIVE LOGITS
    boro
    1.19
    sey
    1.06
    '
    0.97
    haw
    0.90
    cale
    0.85
    hip
    0.81
    borough
    0.79
    ession
    0.78
    ett
    0.78
    hof
    0.77
    Activations Density 0.027%

    No Known Activations