Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7746
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals' names, particularly the name "Joan."

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals and historical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eco
    -0.95
    forward
    -0.88
    irtual
    -0.82
    aneers
    -0.81
    everal
    -0.80
    milo
    -0.78
    nown
    -0.78
    obyl
    -0.76
    ombat
    -0.74
    sites
    -0.73
    POSITIVE LOGITS
    thal
    0.85
    ãĥ³ãĤ¸
    0.72
    ¯¯¯¯
    0.72
    azon
    0.71
     Orc
    0.69
     Carth
    0.68
     Templ
    0.68
     Hamm
    0.67
    Hart
    0.66
     Dynam
    0.66
    Activations Density 0.033%

    No Known Activations