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. 7-RES-JB
    6. 17524
    Prev
    Next
    INDEX
    Explanations

    phrases indicating determination or intention to proceed with something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progression or advancement of actions

    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
    orah
    -0.75
    sat
    -0.69
    ened
    -0.66
    Sah
    -0.66
    affected
    -0.64
    usercontent
    -0.64
    à¨
    -0.64
    she
    -0.64
     ILCS
    -0.63
    ulty
    -0.63
    POSITIVE LOGITS
     regards
    1.13
     regard
    1.04
    draw
    0.92
     respect
    0.84
     preparations
    0.79
    drawn
    0.78
     impunity
    0.78
     caution
    0.75
    holding
    0.74
     utmost
    0.72
    Activations Density 0.068%

    No Known Activations