© 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
    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. 21233
    Prev
    Next
    INDEX
    Explanations

    numbers combined with the abbreviation "nd."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number "2" in various contexts

    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
    gerald
    -0.74
    manship
    -0.61
    00
    -0.59
    ural
    -0.58
     moreover
    -0.56
    iffin
    -0.54
     "$:/
    -0.54
    ured
    -0.53
    ante
    -0.53
     spree
    -0.52
    POSITIVE LOGITS
    nd
    2.05
    ND
    1.18
    147
    1.06
    160
    1.06
    133
    1.05
    shared
    0.98
    245
    0.96
     externalToEVAOnly
    0.96
    187
    0.96
    Pac
    0.96
    Activations Density 0.129%

    No Known Activations