© 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. 11119
    Prev
    Next
    INDEX
    Explanations

    phrases that involve recounting or describing past events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a historical pattern or trend related to various topics

    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
    izons
    -0.84
    assis
    -0.77
    istan
    -0.73
    pload
    -0.71
    hap
    -0.71
    daq
    -0.68
    OTAL
    -0.68
    raints
    -0.67
    bern
    -0.65
     Springer
    -0.65
    POSITIVE LOGITS
     inconsistency
    0.88
     abuse
    0.84
     hostility
    0.80
     excellence
    0.76
     frequent
    0.76
     disruptive
    0.73
     discriminating
    0.72
     tink
    0.72
     accommodating
    0.72
     harassing
    0.72
    Activations Density 0.197%

    No Known Activations