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. 15248
    Prev
    Next
    INDEX
    Explanations

    adjectives describing textures or surfaces

    oai_token-act-pair · gpt-3.5-turbo

    words related to past participles in various contexts

    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
    adra
    -0.75
    SPONSORED
    -0.74
    involved
    -0.72
    icipated
    -0.71
    CVE
    -0.71
    BIT
    -0.65
    Article
    -0.63
    amoto
    -0.62
    went
    -0.61
    noticed
    -0.61
    POSITIVE LOGITS
    river
    1.03
    onite
    1.02
    rive
    0.95
    own
    0.88
    ouble
    0.87
    dit
    0.85
    irect
    0.84
     versions
    0.83
    irection
    0.82
    ness
    0.81
    Activations Density 0.299%

    No Known Activations