© 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. 8-RES-JB
    11. 6434
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning or skepticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing levels of importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atl
    -0.67
     Vide
    -0.67
    LIB
    -0.66
    ROR
    -0.65
     KM
    -0.63
     Gutenberg
    -0.60
    alky
    -0.60
    packages
    -0.60
     Prosper
    -0.59
    ette
    -0.59
    POSITIVE LOGITS
     surely
    1.16
     logically
    1.09
     understandably
    1.06
     naturally
    1.05
     beh
    0.96
     undoubtedly
    0.93
     likely
    0.92
     inevitably
    0.91
     unavoid
    0.91
     shouldn
    0.90
    Activations Density 0.425%

    No Known Activations