© 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. 3740
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking care of a home

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and coordinating phrases in the text

    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
    etheless
    -0.83
    ensis
    -0.81
    irez
    -0.72
     thor
    -0.67
    hement
    -0.66
     reflex
    -0.62
     lect
    -0.61
     mob
    -0.61
    dragon
    -0.60
     toget
    -0.60
    POSITIVE LOGITS
     Kik
    0.83
    76561
    0.77
     Chill
    0.73
    Corp
    0.71
     Bak
    0.71
     Dek
    0.71
     Majesty
    0.70
     Shak
    0.70
    Balt
    0.70
     Bok
    0.69
    Activations Density 1.106%

    No Known Activations