© 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. 3-RES-JB
    11. 6373
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to the word "spider"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word " insider."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     haste
    -0.66
    ë
    -0.62
    ãĥĥãĥĪ
    -0.56
     hearing
    -0.56
     Gazette
    -0.56
     spare
    -0.55
    Hispanic
    -0.55
     Forth
    -0.54
     nonex
    -0.54
     Protestants
    -0.54
    POSITIVE LOGITS
    ider
    0.97
    cair
    0.90
    mares
    0.90
    sonian
    0.86
    ocity
    0.86
    schild
    0.84
    lein
    0.82
    aux
    0.82
    icular
    0.81
    berus
    0.81
    Activations Density 0.015%

    No Known Activations