© 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. 7-RES-JB
    11. 22585
    Prev
    Next
    INDEX
    Explanations

    phrases related to movie titles

    oai_token-act-pair · gpt-3.5-turbo

    references to identifiers or specific titles in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.88
    ocations
    -0.71
    .")
    -0.71
    TPPStreamerBot
    -0.69
    ocating
    -0.65
    indal
    -0.65
    intend
    -0.61
    obar
    -0.60
    ".[
    -0.59
    DragonMagazine
    -0.59
    POSITIVE LOGITS
     âĵĺ
    0.62
     TBD
    0.58
     Koen
    0.57
     Entered
    0.56
     TBA
    0.55
     pg
    0.55
     Yug
    0.55
     Moroc
    0.54
     Nou
    0.54
     Located
    0.54
    Activations Density 0.437%

    No Known Activations