© 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. 12285
    Prev
    Next
    INDEX
    Explanations

    references to the author 'Het' followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific author or publisher

    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
    BuyableInstoreAndOnline
    -0.70
     ranked
    -0.66
    laws
    -0.64
     largeDownload
    -0.63
     viewing
    -0.62
    conservancy
    -0.62
     resemblance
    -0.62
     parallel
    -0.62
     rampant
    -0.61
     solitary
    -0.61
    POSITIVE LOGITS
    het
    1.24
    icals
    1.20
    amines
    1.13
    ype
    1.08
    rette
    1.06
    oric
    1.00
    ty
    0.99
    raq
    0.98
    orically
    0.96
    ypes
    0.95
    Activations Density 0.005%

    No Known Activations