© 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. 8-RES-JB
    11. 20079
    Prev
    Next
    INDEX
    Explanations

    sporting events or competitions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases related to sports events and match results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entimes
    -1.03
    DEF
    -0.89
    sense
    -0.88
    conserv
    -0.88
    published
    -0.86
    typically
    -0.84
    bringing
    -0.83
    conn
    -0.83
    fram
    -0.83
    Secondly
    -0.82
    POSITIVE LOGITS
     TBA
    1.18
     TBD
    0.97
     None
    0.90
     ???
    0.90
     Ro
    0.87
     Lav
    0.86
     V
    0.84
     Bo
    0.83
     Rav
    0.83
     Various
    0.83
    Activations Density 0.208%

    No Known Activations