© 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. 24063
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting elements within the text

    oai_token-act-pair · gpt-3.5-turbo

    symbols and formatting related to lists or itemization

    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
     Lud
    -1.05
    dan
    -0.87
    AUD
    -0.85
    ody
    -0.84
     LU
    -0.77
    TER
    -0.76
    od
    -0.74
    etsk
    -0.73
     Cinnamon
    -0.72
    Dun
    -0.72
    POSITIVE LOGITS
     9
    1.41
    9
    1.38
     Nine
    1.14
     999
    1.05
    Nine
    1.04
     09
    1.03
     nine
    1.02
    nine
    1.01
    909
    0.95
     978
    0.95
    Activations Density 0.271%

    No Known Activations