© 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. 11-RES-JB
    11. 21528
    Prev
    Next
    INDEX
    Explanations

    technical or academic information related to research or publications

    oai_token-act-pair · gpt-3.5-turbo

    specific references to organizations and positions of authority in academia or industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anyway
    -0.92
     rubbish
    -0.83
     organising
    -0.80
     afterwards
    -0.80
     anyways
    -0.80
     realised
    -0.76
     organise
    -0.76
     messing
    -0.75
     downwards
    -0.75
     kinda
    -0.74
    POSITIVE LOGITS
    âĢ
    1.44
    âĢł
    1.20
     âĢ
    1.08
    ®
    1.01
    ®,
    0.98
    »
    0.97
    ¨
    0.96
    ãĢ
    0.93
    âĸł
    0.93
    âĸ
    0.88
    Activations Density 1.083%

    No Known Activations