© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3169
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpretation or analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate perception or interpretation of actions and events

    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
     airst
    -0.78
     Phi
    -0.65
     Horton
    -0.65
     Cah
    -0.64
     stamina
    -0.63
     itch
    -0.63
     occupancy
    -0.63
     veins
    -0.62
     LOT
    -0.62
     coordinates
    -0.62
    POSITIVE LOGITS
    omorphic
    0.90
    hematically
    0.84
    entious
    0.84
    vantage
    0.81
    ãĤ¶
    0.78
    escription
    0.77
     objectively
    0.76
    emporary
    0.74
    rarily
    0.74
    isexual
    0.73
    Activations Density 0.149%

    No Known Activations