© 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. 7-RES-JB
    11. 2121
    Prev
    Next
    INDEX
    Explanations

    phrases that describe something well-known in terms of its particular characteristics or reputation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ownership or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    river
    -0.81
     Rasm
    -0.72
     PLEASE
    -0.70
     Wem
    -0.70
    ievers
    -0.69
    after
    -0.68
     somew
    -0.66
    before
    -0.65
    wrong
    -0.65
    soever
    -0.65
    POSITIVE LOGITS
     own
    1.20
     inability
    1.10
     propensity
    1.04
     unorthodox
    1.01
     versatility
    0.99
     lack
    0.98
     penchant
    0.96
     proximity
    0.95
     portrayal
    0.93
     tendency
    0.93
    Activations Density 0.137%

    No Known Activations