© 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. 6-RES-JB
    11. 7621
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or position, particularly emphasizing something being underneath/below

    oai_token-act-pair · gpt-3.5-turbo

    locations or descriptions related to being above or below surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -1.00
    oly
    -0.73
    etti
    -0.71
    otide
    -0.70
    DN
    -0.69
    istani
    -0.69
    ackers
    -0.68
    onym
    -0.68
    zai
    -0.68
    CHO
    -0.67
    POSITIVE LOGITS
    worldly
    0.87
     foreground
    0.85
     habitable
    0.78
     beneath
    0.78
     inhabited
    0.77
    hung
    0.75
     artif
    0.72
     cliffs
    0.72
     overlooking
    0.71
     corners
    0.71
    Activations Density 0.130%

    No Known Activations