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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23387
    Prev
    Next
    INDEX
    Explanations

    dates and temporal references

    oai_token-act-pair · gpt-3.5-turbo

    common function words and contextual phrases within the text

    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
     Kamp
    -0.75
     Club
    -0.69
     Front
    -0.69
     Muss
    -0.67
     Guard
    -0.63
     Article
    -0.63
     Grail
    -0.63
    edIn
    -0.63
     Peak
    -0.62
     Commander
    -0.62
    POSITIVE LOGITS
    onymous
    0.86
    bsite
    0.84
    terday
    0.81
     guiActiveUn
    0.78
    Þ
    0.74
    anwhile
    0.72
    othermal
    0.70
    otype
    0.70
    hig
    0.69
    olo
    0.69
    Activations Density 0.320%

    No Known Activations