© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16514
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Ax" or similar variations of it

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.85
     Jama
    -0.77
     Nguyen
    -0.76
    Hunt
    -0.72
     Sang
    -0.71
     gren
    -0.70
     Jamaica
    -0.70
    allah
    -0.69
    Privacy
    -0.69
    "}],"
    -0.69
    POSITIVE LOGITS
     ax
    3.57
     Ax
    3.31
    Ax
    2.57
     AX
    2.12
     axes
    1.71
     Axel
    1.57
     axle
    1.45
    AX
    1.45
     induct
    1.39
     axe
    1.38
    Activations Density 0.025%

    No Known Activations