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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 8381
    Prev
    Next
    INDEX
    Explanations

    references to the technology company "Comodo"

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to brands or companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isons
    -0.71
    ////////////////////////////////
    -0.66
     Richie
    -0.64
     CK
    -0.63
    ivating
    -0.62
     rgb
    -0.61
    âĸ¬âĸ¬
    -0.61
     Manny
    -0.61
     Cornell
    -0.60
     seamlessly
    -0.60
    POSITIVE LOGITS
    ulhu
    0.87
    phrine
    0.83
    ership
    0.83
    tenance
    0.79
    Discussion
    0.73
    ctive
    0.73
    _-
    0.72
    DragonMagazine
    0.70
    amus
    0.70
    marine
    0.69
    Activations Density 0.031%

    No Known Activations