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. 677
    Prev
    Next
    INDEX
    Explanations

    varieties of chocolates

    oai_token-act-pair · gpt-3.5-turbo

    topics related to varieties of flavors or colors

    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
    "))
    -0.74
    ciplinary
    -0.64
     attRot
    -0.55
    "!
    -0.54
    resy
    -0.54
     consequently
    -0.52
    ussions
    -0.51
     Practices
    -0.51
    "...
    -0.51
    .?
    -0.50
    POSITIVE LOGITS
    âĨĴ
    0.57
     =>
    0.55
     versus
    0.52
     };
    0.51
     âĨĴ
    0.49
     pse
    0.48
     ($
    0.46
     vs
    0.46
     violin
    0.46
     quartz
    0.46
    Activations Density 1.073%

    No Known Activations