© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16804
    Prev
    Next
    INDEX
    Explanations

    the last name "Huelskamp"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Huelskamp."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     angels
    -0.73
     lightning
    -0.69
     trig
    -0.66
     convenient
    -0.62
     Holy
    -0.62
     Lightning
    -0.62
     abnormal
    -0.60
     Arbit
    -0.58
     thin
    -0.58
     innocent
    -0.57
    POSITIVE LOGITS
    kamp
    5.16
    hower
    1.40
    meier
    1.39
    hof
    1.28
    bach
    1.22
     Kamp
    1.19
    tein
    1.19
    kie
    1.18
    gren
    1.17
    krit
    1.16
    Activations Density 0.022%

    No Known Activations