© 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. 18749
    Prev
    Next
    INDEX
    Explanations

    nouns related to technology and digital communication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to functionality and performance metrics

    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
    aly
    -0.80
    sw
    -0.73
    Otherwise
    -0.71
    SHIP
    -0.66
    Õ
    -0.64
    thumbnails
    -0.62
    alist
    -0.61
    usercontent
    -0.58
    Bey
    -0.58
    اÙĦ
    -0.56
    POSITIVE LOGITS
    omething
    1.22
    ometimes
    1.20
    ilver
    1.18
    pace
    1.16
    hift
    1.15
    creen
    1.14
    heet
    1.12
    afety
    1.05
    paces
    1.05
    pring
    1.04
    Activations Density 0.372%

    No Known Activations