© 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. 8-RES-JB
    11. 18672
    Prev
    Next
    INDEX
    Explanations

    phrases referring to physical actions or interactions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships or positions

    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
     substituted
    -0.67
    fried
    -0.65
     replaced
    -0.63
    orno
    -0.59
     Jarrett
    -0.59
     rewritten
    -0.57
    ghai
    -0.57
     Laksh
    -0.56
    FIG
    -0.56
     accompanied
    -0.56
    POSITIVE LOGITS
    ventory
    0.72
     whom
    0.71
    oba
    0.67
     afar
    0.65
    zeb
    0.65
    insky
    0.64
     deed
    0.64
    xs
    0.63
     advoc
    0.60
    sword
    0.58
    Activations Density 0.445%

    No Known Activations