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. 6-RES-JB
    6. 24003
    Prev
    Next
    INDEX
    Explanations

    instances of actions related to playing or participating in sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports actions involving kicks, shots, and headers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Redd
    -0.78
     dstg
    -0.72
     organising
    -0.70
     living
    -0.70
     membership
    -0.70
     staffing
    -0.69
     Argon
    -0.66
     paed
    -0.66
    ħĭ
    -0.65
    pha
    -0.65
    POSITIVE LOGITS
     misses
    0.92
    tackle
    0.92
    handler
    0.85
    hook
    0.84
    assisted
    0.80
     cutter
    0.79
    lift
    0.78
     whiff
    0.78
     involving
    0.77
     finishes
    0.77
    Activations Density 0.184%

    No Known Activations