© 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. 22519
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in sports or other fields

    oai_token-act-pair · gpt-3.5-turbo

    commas and a specific focus on numerical data

    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
    nih
    -0.70
    ageddon
    -0.68
    aries
    -0.65
    inces
    -0.64
    ities
    -0.64
    aceae
    -0.63
    fo
    -0.61
    atories
    -0.61
    alis
    -0.61
    rooms
    -0.61
    POSITIVE LOGITS
     who
    1.17
    who
    1.10
     whom
    1.03
     undrafted
    1.02
    whose
    1.01
     whose
    1.00
     meanwhile
    0.98
     formerly
    0.90
     drafted
    0.90
     acquired
    0.88
    Activations Density 0.106%

    No Known Activations