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. 17964
    Prev
    Next
    INDEX
    Explanations

    references to people lying down in various settings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations or positions

    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
    thood
    -0.76
    ividual
    -0.71
    bear
    -0.71
    uria
    -0.69
    rates
    -0.68
    IRC
    -0.67
    ategory
    -0.67
    iac
    -0.66
    upon
    -0.66
    taboola
    -0.65
    POSITIVE LOGITS
     doorstep
    1.12
     outskirts
    1.10
     pavement
    1.09
     ledge
    1.09
     porch
    1.08
     sidewalk
    1.06
     sidelines
    1.05
     brink
    1.04
     sofa
    1.03
     floor
    1.02
    Activations Density 0.191%

    No Known Activations