© 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. 9-RES-JB
    11. 4984
    Prev
    Next
    INDEX
    Explanations

    length measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating measurements or dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    eers
    -0.91
    eer
    -0.79
    dinand
    -0.79
    ILLE
    -0.75
    eering
    -0.75
    unin
    -0.70
    agne
    -0.65
     Jarrett
    -0.64
     Belle
    -0.63
    tical
    -0.61
    POSITIVE LOGITS
    iest
    1.00
     lengths
    0.93
    wise
    0.92
     length
    0.91
    ways
    0.90
    shed
    0.88
    iness
    0.84
    running
    0.81
    ftime
    0.78
    cut
    0.77
    Activations Density 0.024%

    No Known Activations