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. 0-RES-JB
    6. 21883
    Prev
    Next
    INDEX
    Explanations

    words related to speaking or communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of speaking or singing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solitaire
    -0.73
     sunset
    -0.64
     difficulty
    -0.60
     Sunset
    -0.60
     freezing
    -0.58
     eas
    -0.57
     beta
    -0.55
     Twilight
    -0.54
     blocking
    -0.54
    oug
    -0.53
    POSITIVE LOGITS
     speaks
    3.39
     speak
    1.98
     spoke
    1.83
     communicates
    1.80
     listens
    1.54
     reflects
    1.51
     discusses
    1.51
     expresses
    1.50
     translates
    1.49
     sings
    1.44
    Activations Density 0.017%

    No Known Activations