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. 9-RES-JB
    6. 6731
    Prev
    Next
    INDEX
    Explanations

    requests or mentions of asking for specific things or help

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the act of asking for help or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alth
    -0.87
    ient
    -0.79
    pire
    -0.74
    Wars
    -0.71
    enium
    -0.69
    oppable
    -0.69
    ondo
    -0.69
    ãĥĦ
    -0.68
    bleacher
    -0.68
    beit
    -0.66
    POSITIVE LOGITS
     forgiveness
    1.47
     clarification
    1.36
     permission
    1.34
     assistance
    1.19
     help
    1.12
     advice
    1.12
     mercy
    1.11
     directions
    1.08
     patience
    1.02
     favors
    1.02
    Activations Density 0.119%

    No Known Activations