© 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. 1-RES-JB
    11. 20113
    Prev
    Next
    INDEX
    Explanations

    terms related to high-level programming languages

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to high-level skills or expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nur
    -0.71
    lez
    -0.67
     Territories
    -0.67
     Noct
    -0.65
     vot
    -0.64
     Andromeda
    -0.63
    ãĥĹ
    -0.63
     Ruk
    -0.62
     Slip
    -0.62
     galaxy
    -0.62
    POSITIVE LOGITS
    level
    1.21
    Level
    0.90
    levels
    0.87
     levels
    0.82
    quartered
    0.81
     level
    0.77
    casting
    0.74
    ahead
    0.74
    afety
    0.73
    hyde
    0.71
    Activations Density 0.010%

    No Known Activations