© 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. 21736
    Prev
    Next
    INDEX
    Explanations

    the name "Kurt" at different levels of context

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kurt" and its associated context

    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
    hare
    -0.76
    cale
    -0.68
    士
    -0.64
    hip
    -0.64
    maid
    -0.63
    ITED
    -0.61
    ILA
    -0.59
    ciation
    -0.58
    atories
    -0.58
     Examiner
    -0.58
    POSITIVE LOGITS
    zman
    1.22
    tering
    1.04
     Von
    1.03
    osis
    0.99
    inous
    0.97
     Angle
    0.96
     Ops
    0.96
    z
    0.88
    ting
    0.88
    inations
    0.85
    Activations Density 0.029%

    No Known Activations