© 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. 2-RES-JB
    11. 12416
    Prev
    Next
    INDEX
    Explanations

    objects or items used as accessories in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to props and acknowledgments in creative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferry
    -0.67
     Ley
    -0.66
     Kuala
    -0.64
    mong
    -0.64
     explor
    -0.63
     Sicily
    -0.63
    ournal
    -0.63
     mosquit
    -0.62
     Eg
    -0.62
     bombers
    -0.61
    POSITIVE LOGITS
    Congratulations
    0.93
     thank
    0.88
     congr
    0.86
    udos
    0.83
    rats
    0.80
     Congratulations
    0.80
     props
    0.80
     thanking
    0.80
    hirt
    0.76
    Thanks
    0.76
    Activations Density 0.014%

    No Known Activations