© 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. 4-RES-JB
    11. 14843
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a noun phrase referring to the location of an object

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and articles associated with locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.92
    arily
    -0.80
    20439
    -0.78
     reperto
    -0.77
    CIA
    -0.76
    wcs
    -0.75
    dayName
    -0.74
    CW
    -0.73
    Ô
    -0.72
    inctions
    -0.70
    POSITIVE LOGITS
     Appalach
    0.80
     course
    0.76
     Sutherland
    0.70
    gall
    0.70
     each
    0.68
     Gors
    0.67
    yx
    0.64
     stairs
    0.63
     Dover
    0.63
     the
    0.63
    Activations Density 0.149%

    No Known Activations