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. 2810
    Prev
    Next
    INDEX
    Explanations

    descriptive terms expressing evaluation or observation of a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to challenges and dynamics within social or political 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
    ?".
    -0.70
    catentry
    -0.66
    CLASSIFIED
    -0.61
    byter
    -0.61
    azed
    -0.61
    Rated
    -0.60
    Its
    -0.60
     Written
    -0.59
    ".[
    -0.58
     Needless
    -0.58
    POSITIVE LOGITS
     here
    1.29
     nowadays
    1.04
     insofar
    0.97
     when
    0.89
     herein
    0.81
     today
    0.76
     HERE
    0.75
     these
    0.74
    enance
    0.71
     rhet
    0.70
    Activations Density 0.605%

    No Known Activations