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

    Neuronpedia

    APICircuit 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. 15534
    Prev
    Next
    INDEX
    Explanations

    actions related to communication or interaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the action of reaching out or extending connections

    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
    timer
    -0.68
    how
    -0.64
    ickr
    -0.63
    atto
    -0.60
    MORE
    -0.60
    ech
    -0.59
    weather
    -0.59
     EVENTS
    -0.57
    matter
    -0.56
    ussen
    -0.55
    POSITIVE LOGITS
     conclusions
    1.03
     out
    0.90
     heights
    0.88
     adulthood
    0.86
     speeds
    0.85
     consensus
    0.85
     fruition
    0.85
     lengths
    0.83
     saturation
    0.82
     agreement
    0.81
    Activations Density 0.047%

    No Known Activations