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. 15167
    Prev
    Next
    INDEX
    Explanations

    senior roles or positions within organizations

    oai_token-act-pair · gpt-3.5-turbo

    job titles and roles in professional 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
    sbm
    -0.66
     announ
    -0.60
     understatement
    -0.58
    stood
    -0.58
    asted
    -0.57
     reper
    -0.57
     commentators
    -0.56
    ATCH
    -0.56
    pload
    -0.55
     strangers
    -0.55
    POSITIVE LOGITS
     for
    1.10
     extraord
    1.00
     at
    0.91
    hips
    0.86
     with
    0.80
    @
    0.78
     specializing
    0.76
    iant
    0.75
     emer
    0.71
    for
    0.68
    Activations Density 0.110%

    No Known Activations