© 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. 7606
    Prev
    Next
    INDEX
    Explanations

    terms related to reaching goals or making progress

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical discomfort or pain

    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
    otine
    -0.86
     stocking
    -0.83
     tiss
    -0.72
     reserv
    -0.68
    drm
    -0.68
     printers
    -0.68
    demand
    -0.67
    powder
    -0.67
     Frie
    -0.65
    adder
    -0.65
    POSITIVE LOGITS
    ingly
    0.88
    DonaldTrump
    0.87
    ions
    0.84
    ments
    0.75
    idon
    0.75
    ibility
    0.71
    kat
    0.70
    ippi
    0.70
    ional
    0.69
    baugh
    0.69
    Activations Density 0.014%

    No Known Activations