© 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. 9416
    Prev
    Next
    INDEX
    Explanations

    statistical or numerical information in the text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of comparisons and statistical measures

    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
    Introduced
    -0.65
    NetMessage
    -0.65
    dayName
    -0.64
    arella
    -0.61
    DF
    -0.61
    ér
    -0.60
    azon
    -0.60
     Joined
    -0.59
    movie
    -0.58
     Blog
    -0.57
    POSITIVE LOGITS
     unheard
    1.04
     peanuts
    1.00
     equivalent
    1.00
     astronomical
    0.96
     respectable
    0.96
     unacceptable
    0.96
     impressive
    0.95
     unsustainable
    0.94
     dwar
    0.92
     comparable
    0.92
    Activations Density 0.144%

    No Known Activations