© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 2449
    Prev
    Next
    INDEX
    Explanations

    numeric patterns, possibly in the form of lists or bullet points, and possibly with some variation in format

    oai_token-act-pair · gpt-3.5-turbo

    isolated punctuation or numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seventy
    -1.05
     fifty
    -1.04
     sixteen
    -1.00
     nineteen
    -0.97
     sixty
    -0.97
     thirty
    -0.97
     seventeen
    -0.95
     twenty
    -0.95
     eighteen
    -0.95
     fifteen
    -0.95
    POSITIVE LOGITS
    2
    1.95
    3
    1.92
    4
    1.75
    1
    1.59
    5
    1.47
    6
    1.39
    7
    1.23
    8
    1.16
    9
    1.15
    Pros
    1.09
    Activations Density 0.114%

    No Known Activations