© 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. 9-RES-JB
    11. 6855
    Prev
    Next
    INDEX
    Explanations

    phrases related to making decisions or offering suggestions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invariably
    -0.66
     ALWAYS
    -0.62
     relentlessly
    -0.60
     uniformly
    -0.60
    ocracy
    -0.59
     overwhelmingly
    -0.58
    always
    -0.58
    ulner
    -0.57
     basically
    -0.57
     constantly
    -0.55
    POSITIVE LOGITS
     someday
    1.13
     tempted
    0.81
     inadvertently
    0.80
     unintentionally
    0.74
     misunder
    0.73
     unwittingly
    0.73
    xus
    0.70
    ivably
    0.68
    TAIN
    0.67
     somew
    0.65
    Activations Density 0.276%

    No Known Activations