© 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. 20464
    Prev
    Next
    INDEX
    Explanations

    sentences related to arguments, debates, and discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases about the duality or contrast between different entities or ideas

    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
    Kings
    -0.86
    BBC
    -0.85
    Magic
    -0.82
    veyard
    -0.76
    Matthew
    -0.74
    Golden
    -0.73
    olitan
    -0.73
     Passenger
    -0.71
    Knight
    -0.71
    attery
    -0.69
    POSITIVE LOGITS
    ÂŃ
    1.44
     stru
    1.39
     sup
    1.31
     includ
    1.26
     cov
    1.20
     Demo
    1.18
     dur
    1.17
     polit
    1.13
     prin
    1.13
     Amer
    1.12
    Activations Density 0.069%

    No Known Activations