© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23951
    Prev
    Next
    INDEX
    Explanations

    information related to data analysis or investigation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the usefulness of data for decision-making and understanding

    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
    shr
    -0.76
     Cursed
    -0.66
    yd
    -0.65
     fucked
    -0.63
     Nope
    -0.63
     screwed
    -0.62
     cel
    -0.61
     bailed
    -0.61
     disliked
    -0.60
     sacrificed
    -0.59
    POSITIVE LOGITS
     insights
    1.08
     decipher
    1.04
     insight
    1.02
     analyse
    0.94
     understanding
    0.91
     conclusions
    0.90
     enlight
    0.89
     dissemination
    0.89
     qualitative
    0.88
     analyze
    0.88
    Activations Density 0.699%

    No Known Activations