© 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. 1-RES-JB
    11. 3524
    Prev
    Next
    INDEX
    Explanations

    terms related to support or approval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to highlighting important information or events

    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
     cloud
    -0.79
    cap
    -0.73
    beam
    -0.72
    hu
    -0.70
    hill
    -0.69
    press
    -0.69
    cor
    -0.68
    cloud
    -0.68
     acres
    -0.67
    atti
    -0.66
    POSITIVE LOGITS
    zsche
    0.96
    reditary
    0.95
     compr
    0.87
     subsequ
    0.84
    ngth
    0.81
     disadvant
    0.80
    ntil
    0.79
    tainment
    0.78
    nesses
    0.78
     obser
    0.74
    Activations Density 0.171%

    No Known Activations