© 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. 10-RES-JB
    11. 20273
    Prev
    Next
    INDEX
    Explanations

    references to specific models and versions of electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to specific smartphone models and their capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asha
    -0.69
    iques
    -0.67
    cloth
    -0.66
    hesda
    -0.66
    anooga
    -0.65
     legislator
    -0.64
    science
    -0.64
    hya
    -0.64
    banks
    -0.63
    gob
    -0.63
    POSITIVE LOGITS
     onwards
    1.04
     onward
    1.02
     II
    0.96
     subsequent
    0.92
     XV
    0.89
     thereafter
    0.88
     later
    0.87
     Anniversary
    0.86
     above
    0.86
     Beyond
    0.85
    Activations Density 0.157%

    No Known Activations