© 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. 16704
    Prev
    Next
    INDEX
    Explanations

    actors' names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or individuals, particularly notable figures or companies

    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
     chees
    -0.89
    wcsstore
    -0.87
    rez
    -0.77
     gel
    -0.74
    ãĤª
    -0.74
    abad
    -0.74
    agan
    -0.73
    azel
    -0.73
     mu
    -0.72
     haz
    -0.72
    POSITIVE LOGITS
     Th
    2.51
    Th
    2.30
     TH
    1.94
     th
    1.74
    TH
    1.61
     Thur
    1.45
    th
    1.39
     Thorn
    1.39
     Thr
    1.33
     THR
    1.23
    Activations Density 0.216%

    No Known Activations