© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 2578
    Prev
    Next
    INDEX
    Explanations

    measurements related to lengths or distances

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of distance in feet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [+
    -0.69
    MRI
    -0.69
    PsyNetMessage
    -0.67
    bid
    -0.67
    ULE
    -0.66
    urally
    -0.65
    vertis
    -0.65
    ãĥ´ãĤ¡
    -0.65
     Rohing
    -0.64
     Null
    -0.64
    POSITIVE LOGITS
     feet
    1.10
     Feet
    1.06
    hops
    0.99
     paws
    0.92
    bridge
    0.89
    feet
    0.87
    gypt
    0.82
     tapping
    0.77
    pring
    0.77
     pedals
    0.76
    Activations Density 0.010%

    No Known Activations