© 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. 10310
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors for various situations and experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional reactions or opinions

    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
    ð
    -0.68
    ·
    -0.67
    tains
    -0.66
    lio
    -0.66
    Featured
    -0.66
    continue
    -0.63
    pro
    -0.62
    donald
    -0.62
    bies
    -0.61
     ("
    -0.61
    POSITIVE LOGITS
     certainly
    0.83
    ngth
    0.80
     definitely
    0.71
     gonna
    0.67
     gotta
    0.67
     Journals
    0.66
     defin
    0.66
    oret
    0.65
    yss
    0.62
    ĸļ
    0.62
    Activations Density 0.806%

    No Known Activations