© 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. 3016
    Prev
    Next
    INDEX
    Explanations

    discussions related to accountability and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events, actions, or dynamics involving individuals or groups

    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
     Notting
    -0.61
     CCTV
    -0.59
     Surrey
    -0.58
     Canaver
    -0.58
     MDMA
    -0.56
    ibaba
    -0.54
     Loud
    -0.54
     Slater
    -0.53
     Kabul
    -0.53
    itsch
    -0.52
    POSITIVE LOGITS
    Others
    1.10
     ones
    0.96
    those
    0.93
     others
    0.89
     exceptions
    0.87
    these
    0.84
     Others
    0.83
    Similarly
    0.80
    Other
    0.77
     replacements
    0.77
    Activations Density 1.229%

    No Known Activations