© 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. 10-RES-JB
    11. 14184
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs related to the evaluation of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or acknowledgment of helpfulness

    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
    retty
    -0.49
    izoph
    -0.48
    ô
    -0.47
     Moroc
    -0.47
    farious
    -0.45
    UFF
    -0.42
     Instr
    -0.42
    uman
    -0.41
    adel
    -0.41
    kan
    -0.40
    POSITIVE LOGITS
     to
    1.28
    to
    0.95
     TO
    0.88
     To
    0.86
    To
    0.85
     thereto
    0.83
     unto
    0.81
     ta
    0.67
    TO
    0.61
    DragonMagazine
    0.60
    Activations Density 1.018%

    No Known Activations