© 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. 5138
    Prev
    Next
    INDEX
    Explanations

    references to physical injuries, specifically focusing on tears or damage

    oai_token-act-pair · gpt-3.5-turbo

    mentions of something being torn, often in a physical or emotional context

    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
    lain
    -0.81
    VERTISEMENT
    -0.75
    perty
    -0.71
    racuse
    -0.70
    ITNESS
    -0.68
    cius
    -0.66
    susp
    -0.66
    Sing
    -0.66
    travel
    -0.65
    arten
    -0.65
    POSITIVE LOGITS
    adoes
    1.49
    ados
    1.01
    adic
    0.93
     apart
    0.86
    away
    0.86
     belts
    0.81
    owship
    0.78
     ACL
    0.76
     unprotected
    0.74
    neck
    0.73
    Activations Density 0.017%

    No Known Activations