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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5867
    Prev
    Next
    INDEX
    Explanations

    splits of baseball statistics like batting averages and results, focusing particularly on the slash line format "<hits>/<at bats>/<slugging percentage>"

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or numerical values

    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
     Survivors
    -0.72
     Toys
    -0.65
     Ferr
    -0.65
     Wend
    -0.65
     Hills
    -0.64
     actors
    -0.64
     Debor
    -0.64
     Flav
    -0.64
     Constantin
    -0.63
     Orn
    -0.63
    POSITIVE LOGITS
     cubic
    0.79
    333
    0.78
    431
    0.77
    RFC
    0.77
    220
    0.76
    etc
    0.76
    ãĥĺ
    0.76
    15
    0.76
    Pg
    0.75
    16
    0.75
    Activations Density 0.014%

    No Known Activations