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. 9796
    Prev
    Next
    INDEX
    Explanations

    words related to people's names or places

    oai_token-act-pair · gpt-3.5-turbo

    words related to concepts that end with "ary," indicating a focus on terminology associated with various fields, possibly scientific or literary classifications

    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
    essee
    -0.68
     DMV
    -0.63
    ļéĨĴ
    -0.62
    ossibility
    -0.61
     Survivor
    -0.58
    å°Ĩ
    -0.58
    ided
    -0.57
     Variant
    -0.56
    ossier
    -0.56
    ilot
    -0.56
    POSITIVE LOGITS
    ary
    0.99
    ARY
    0.89
    anse
    0.83
    aries
    0.80
    otes
    0.76
    ature
    0.76
    adh
    0.76
    ansas
    0.75
    aris
    0.71
    abama
    0.71
    Activations Density 0.010%

    No Known Activations