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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RES-JB
    6. 24441
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and programming code structures

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses and nested structures in the text

    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
     Bever
    -0.75
     Edison
    -0.68
     bills
    -0.66
     Tus
    -0.65
     ultr
    -0.65
     debts
    -0.65
     Bian
    -0.64
     Scientology
    -0.64
     altogether
    -0.63
     journalism
    -0.63
    POSITIVE LOGITS
    lambda
    1.39
    require
    1.30
    ++)
    1.16
    define
    1.14
    λ
    1.13
     lambda
    1.12
    assuming
    1.11
    equal
    1.11
    insert
    1.10
    repeat
    1.09
    Activations Density 0.043%

    No Known Activations