© 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. 9-RES-JB
    11. 9063
    Prev
    Next
    INDEX
    Explanations

    special characters, technical terms, and code-related words

    oai_token-act-pair · gpt-3.5-turbo

    specific technical or scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hindsight
    -0.61
     oneself
    -0.60
     sidx
    -0.59
     apologies
    -0.59
     yourselves
    -0.56
     ourselves
    -0.55
     carefully
    -0.53
    DragonMagazine
    -0.53
     mend
    -0.52
     pleas
    -0.52
    POSITIVE LOGITS
    ensis
    0.83
    astery
    0.77
    orum
    0.73
    ixture
    0.73
    ride
    0.72
    istries
    0.69
    agogue
    0.66
     Remix
    0.64
    insula
    0.64
    adas
    0.63
    Activations Density 0.767%

    No Known Activations