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. 8-RES-JB
    6. 9676
    Prev
    Next
    INDEX
    Explanations

    things that are located at a higher position relative to other objects

    oai_token-act-pair · gpt-3.5-turbo

    positions or locations in relation to "above" or "behind."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Introduced
    -0.77
    DN
    -0.71
    alysis
    -0.71
    IPP
    -0.71
    ̶
    -0.69
    agically
    -0.68
    uten
    -0.68
    士
    -0.67
    iasis
    -0.66
    oglu
    -0.66
    POSITIVE LOGITS
    rium
    1.03
    hang
    0.85
    tyard
    0.80
     midnight
    0.79
    hung
    0.79
     foreground
    0.77
     infinity
    0.77
     them
    0.75
     dusk
    0.73
     the
    0.73
    Activations Density 0.192%

    No Known Activations