© 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. 6-RES-JB
    11. 17184
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating increasing levels or degrees of a quality or action

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases highlighting increasing or decreasing complexity or severity

    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
    hof
    -0.72
    apesh
    -0.69
    pb
    -0.68
    inside
    -0.67
    bart
    -0.66
    Haw
    -0.66
    utch
    -0.66
    ums
    -0.65
    âĢİ
    -0.65
    osures
    -0.64
    POSITIVE LOGITS
     chances
    0.75
     likely
    0.69
     likelihood
    0.69
     chance
    0.67
     amount
    0.64
     probability
    0.62
     Dame
    0.62
    natureconservancy
    0.62
     temptation
    0.62
     surely
    0.59
    Activations Density 0.093%

    No Known Activations