© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22864
    Prev
    Next
    INDEX
    Explanations

    adjectives related to basic, unprocessed, or original form

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "raw" materials or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itism
    -0.82
    etheless
    -0.82
    uyomi
    -0.79
    agall
    -0.78
    ŃĶ
    -0.78
    ommel
    -0.75
    agements
    -0.73
    eanor
    -0.71
    aternity
    -0.71
     Explain
    -0.70
    POSITIVE LOGITS
    hide
    1.41
     sewage
    1.07
    lings
    1.04
     materials
    0.98
    ls
    0.98
    esome
    0.90
    lins
    0.88
     raw
    0.84
    blood
    0.82
     material
    0.80
    Activations Density 0.014%

    No Known Activations