© 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. 7617
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate outcomes or results related to various subjects

    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
    oyal
    -0.72
    ielding
    -0.67
    SPONSORED
    -0.67
    fulness
    -0.67
    iveness
    -0.66
    livious
    -0.65
    taboola
    -0.63
    ruciating
    -0.63
    upload
    -0.62
    maximum
    -0.62
    POSITIVE LOGITS
    furt
    0.84
     Mour
    0.73
     fray
    0.71
     ze
    0.65
     smelling
    0.64
    regor
    0.63
    zag
    0.63
     bye
    0.62
     mur
    0.62
     swinging
    0.61
    Activations Density 0.185%

    No Known Activations