© 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. 10-RES-JB
    11. 8576
    Prev
    Next
    INDEX
    Explanations

    website links or URLs

    oai_token-act-pair · gpt-3.5-turbo

    sentences that function as links or references for additional content

    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
     tremend
    -0.84
     metic
    -0.79
     mosqu
    -0.78
     imperson
    -0.77
     strugg
    -0.72
     awakening
    -0.71
     plurality
    -0.70
     oun
    -0.70
     stereotyp
    -0.69
     halting
    -0.69
    POSITIVE LOGITS
    <|endoftext|>
    1.55
     Alternatively
    1.37
     Also
    1.30
    ↵
    1.15
     Includes
    1.15
     Additionally
    1.13
     Subscribe
    1.11
     Lastly
    1.10
     Otherwise
    1.08
    ↵↵
    1.08
    Activations Density 0.120%

    No Known Activations