© 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. 10-RES-JB
    11. 14089
    Prev
    Next
    INDEX
    Explanations

    references to locations or settings within a scene

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and spatial relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.75
     Cosponsors
    -0.73
     DRAG
    -0.70
    nesses
    -0.67
     Parables
    -0.66
    uador
    -0.66
    auts
    -0.66
    MpServer
    -0.65
    icans
    -0.65
    oric
    -0.65
    POSITIVE LOGITS
     beck
    0.91
     indicating
    0.86
     waiting
    0.86
     ready
    0.80
     dotted
    0.77
     besides
    0.77
     reminding
    0.75
     proclaiming
    0.75
     somewhere
    0.74
     resembling
    0.73
    Activations Density 0.308%

    No Known Activations