© 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. 23646
    Prev
    Next
    INDEX
    Explanations

    words related to writing or data manipulation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of writing-related terms and commands

    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
    Ĭ±
    -0.81
    ensis
    -0.80
    alian
    -0.79
     Goodman
    -0.76
    nels
    -0.71
    EGA
    -0.71
    ificent
    -0.71
    avorite
    -0.71
     Ezek
    -0.70
    Ĥª
    -0.70
    POSITIVE LOGITS
     instrument
    0.75
    RAM
    0.73
     typed
    0.72
    gres
    0.68
    lishing
    0.68
    manship
    0.67
    sequ
    0.65
    smanship
    0.65
    phrine
    0.65
    à©
    0.65
    Activations Density 0.046%

    No Known Activations