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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 17927
    Prev
    Next
    INDEX
    Explanations

    words related to expansion or growth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expansion or increase in various contexts

    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
    ball
    -0.79
    footed
    -0.78
    warts
    -0.73
    âĸ¬âĸ¬
    -0.73
    milo
    -0.69
     principals
    -0.67
    balls
    -0.67
    FACE
    -0.66
    ezvous
    -0.65
    MET
    -0.65
    POSITIVE LOGITS
    onential
    1.42
    ansion
    1.38
    ulsion
    1.33
    onent
    1.32
    osed
    1.30
    anded
    1.29
    ression
    1.26
    anding
    1.16
    ressive
    1.12
    ressed
    1.12
    Activations Density 0.012%

    No Known Activations