© 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. 5058
    Prev
    Next
    INDEX
    Explanations

    words related to negative actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal or criminal terminology

    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
     Lauder
    -0.76
     Shepherd
    -0.75
     Wol
    -0.69
     Worlds
    -0.68
     Ruler
    -0.67
     Leilan
    -0.67
     Beetle
    -0.66
     Tile
    -0.64
     Cot
    -0.64
     Sph
    -0.64
    POSITIVE LOGITS
    actly
    1.13
    withstanding
    1.13
    mediately
    1.08
    initely
    1.05
    ardless
    1.02
    erved
    1.01
    tenance
    0.99
    ategic
    0.99
    ificantly
    0.98
    taining
    0.98
    Activations Density 0.227%

    No Known Activations