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. 7-RES-JB
    6. 6722
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement or operation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "run" and its variations in different contexts

    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
     Plain
    -0.68
    ighter
    -0.64
    ayers
    -0.64
    iden
    -0.63
    actory
    -0.62
    grave
    -0.61
     Flavoring
    -0.60
    axter
    -0.60
    alam
    -0.60
    ault
    -0.58
    POSITIVE LOGITS
    around
    0.86
    gs
    0.84
    dy
    0.80
     concurrently
    0.79
    lasses
    0.78
    cul
    0.78
    estones
    0.78
    aways
    0.78
    Disney
    0.76
     smoothly
    0.76
    Activations Density 0.047%

    No Known Activations