© 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. 2589
    Prev
    Next
    INDEX
    Explanations

    long, complex words or phrases related to description or analysis

    oai_token-act-pair · gpt-3.5-turbo

    actions or activities that imply change or development

    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
    RET
    -0.71
    ahime
    -0.65
     Flavoring
    -0.64
    Pros
    -0.62
    essen
    -0.61
    atever
    -0.59
    ennes
    -0.58
    %.
    -0.57
    USS
    -0.57
    $.
    -0.56
    POSITIVE LOGITS
     differed
    1.18
     consisted
    1.16
     differs
    1.10
     depended
    1.09
     amounted
    1.07
     belonged
    1.06
     weren
    1.05
     corresponds
    1.05
     involves
    1.05
     lacked
    1.04
    Activations Density 0.278%

    No Known Activations