© 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. 17065
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases beginning with "at" or "of"

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and related phrases indicating time or location

    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
    IT
    -0.66
    REP
    -0.61
    æĸ¹
    -0.61
    REL
    -0.59
    adia
    -0.59
     ©
    -0.57
    Ħ¢
    -0.57
    Hub
    -0.56
    BF
    -0.55
    malink
    -0.54
    POSITIVE LOGITS
     whom
    1.47
     which
    1.44
    which
    1.29
     whose
    1.06
     Which
    1.02
    whose
    1.02
    Which
    0.98
     whence
    0.93
    lining
    0.87
    cluding
    0.82
    Activations Density 0.209%

    No Known Activations