© 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. 4-RES-JB
    11. 3937
    Prev
    Next
    INDEX
    Explanations

    phrases expressing permission or approval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or acceptance

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

    No Comments

    Negative Logits
    hani
    -0.80
    marine
    -0.79
    ulhu
    -0.75
    raped
    -0.70
    riber
    -0.65
    ocrat
    -0.64
    ulator
    -0.62
    enegger
    -0.61
    leneck
    -0.61
    hunt
    -0.60
    POSITIVE LOGITS
    AY
    0.91
    lahoma
    0.83
     okay
    0.69
     HOME
    0.68
     alright
    0.66
     bye
    0.65
    terday
    0.65
     ok
    0.65
     margin
    0.64
     margins
    0.64
    Activations Density 0.018%

    No Known Activations