© 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. 21302
    Prev
    Next
    INDEX
    Explanations

    phrases with hyphenated words indicating criticism or negation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating social status or wealth, particularly those prefixed with "well-"

    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
     Hancock
    -0.70
     Creator
    -0.70
     Territory
    -0.69
     Cutter
    -0.69
     submission
    -0.67
     expiration
    -0.67
     canvas
    -0.66
     eviction
    -0.66
     DOI
    -0.66
     commencement
    -0.66
    POSITIVE LOGITS
    known
    1.74
    documented
    1.59
    established
    1.59
    equipped
    1.55
    respected
    1.54
    intention
    1.52
    trained
    1.51
    meaning
    1.51
    connected
    1.48
    rounded
    1.48
    Activations Density 0.022%

    No Known Activations