Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18966
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Guillen"

    oai_token-act-pair · gpt-3.5-turbo

    variants of the word "kill" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    в
    -0.59
    ccording
    -0.58
    BOOK
    -0.57
    lished
    -0.56
    resy
    -0.56
    eling
    -0.56
     Older
    -0.56
     Cage
    -0.55
    eled
    -0.55
    [_
    -0.55
    POSITIVE LOGITS
    espie
    1.59
    uminati
    1.48
    iard
    1.24
    inois
    1.23
    iam
    1.23
    ennial
    1.19
    ustration
    1.17
    iant
    1.08
    otine
    1.08
    iman
    1.06
    Activations Density 0.042%

    No Known Activations