© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 8590
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives or descriptions indicating degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives or descriptors indicating size, quality, or strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.69
     accomp
    -0.63
    conservancy
    -0.62
     PARK
    -0.61
     Dul
    -0.58
     Âł Âł Âł Âł
    -0.58
     conduc
    -0.57
     SHE
    -0.57
     sanctioned
    -0.57
     Pok
    -0.57
    POSITIVE LOGITS
    er
    2.46
    est
    2.23
    nesses
    1.64
    ly
    1.57
    erness
    1.52
    ing
    1.46
    erd
    1.43
    itudinal
    1.43
    ers
    1.42
    erate
    1.41
    Activations Density 0.150%

    No Known Activations