© 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. 8-RES-JB
    11. 6473
    Prev
    Next
    INDEX
    Explanations

    words related to division, partitions, or separating objects into different parts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "div" indicating various divisions or separations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SEE
    -0.74
     lodge
    -0.68
     Rivals
    -0.68
     earnest
    -0.65
     Herald
    -0.65
    seeing
    -0.63
     Wolves
    -0.63
    eele
    -0.62
    akeru
    -0.61
     Erit
    -0.61
    POSITIVE LOGITS
    isions
    1.49
    isible
    1.41
    isive
    1.32
    ision
    1.32
    orce
    1.28
    ination
    1.25
    inatory
    1.21
    inity
    1.13
    inations
    1.12
    inyl
    1.12
    Activations Density 0.029%

    No Known Activations