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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16108
    Prev
    Next
    INDEX
    Explanations

    dates or specific numbers related to legal or investigative activities

    oai_token-act-pair · gpt-3.5-turbo

    information related to investigations and reports of criminal activities

    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
    rawdownloadcloneembedreportprint
    -0.83
    tera
    -0.72
     metaphors
    -0.71
     Talks
    -0.70
    Cooldown
    -0.70
    atra
    -0.69
    externalActionCode
    -0.66
    eworld
    -0.66
     luxury
    -0.63
     Cooldown
    -0.62
    POSITIVE LOGITS
     found
    1.57
     finding
    1.50
     findings
    1.45
    found
    1.41
     discovered
    1.38
     uncovered
    1.30
     concluded
    1.27
     finds
    1.26
     detected
    1.26
     concluding
    1.19
    Activations Density 0.601%

    No Known Activations