© 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. 7-RES-JB
    11. 24572
    Prev
    Next
    INDEX
    Explanations

    actions related to personal grooming, such as showering and shaving

    oai_token-act-pair · gpt-3.5-turbo

    references to bathing or grooming activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLASSIFIED
    -0.77
    SEE
    -0.71
    sup
    -0.68
    iev
    -0.65
    HCR
    -0.63
    é»Ĵ
    -0.63
     issu
    -0.63
    eno
    -0.62
     Seg
    -0.61
     Afric
    -0.60
    POSITIVE LOGITS
    utic
    0.93
    ipper
    0.92
    pling
    0.88
    apers
    0.85
    ittal
    0.85
    pled
    0.84
    bing
    0.81
    ption
    0.81
    ı
    0.79
    ippers
    0.79
    Activations Density 0.051%

    No Known Activations