© 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. 14877
    Prev
    Next
    INDEX
    Explanations

    words related to reporting or pointing out activities or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating directionality or movement

    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
    SPONSORED
    -0.90
     McAuliffe
    -0.65
    etheus
    -0.59
     Harvest
    -0.58
     Photograph
    -0.57
    reflect
    -0.56
     Fitzgerald
    -0.56
     WATCH
    -0.55
    iott
    -0.54
    GREEN
    -0.54
    POSITIVE LOGITS
    geon
    0.77
     bushes
    0.63
    utsche
    0.62
     corpse
    0.62
     toe
    0.61
     Dragonbound
    0.61
    ogie
    0.59
     lifeless
    0.59
    Downloadha
    0.58
    dit
    0.58
    Activations Density 0.719%

    No Known Activations