© 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. 6-RES-JB
    11. 7306
    Prev
    Next
    INDEX
    Explanations

    phrases referring to actions or descriptions involving oneself

    oai_token-act-pair · gpt-3.5-turbo

    references to the self or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grain
    -0.80
    profits
    -0.77
    encies
    -0.75
     Seym
    -0.75
    veyard
    -0.74
    microsoft
    -0.73
    vertisements
    -0.71
     revolutions
    -0.69
    sweet
    -0.67
    rush
    -0.67
    POSITIVE LOGITS
     himself
    0.86
     personally
    0.78
     underwater
    0.75
     onstage
    0.70
     mate
    0.70
     admitted
    0.70
     confessed
    0.70
     profess
    0.69
    etz
    0.67
     admits
    0.66
    Activations Density 0.030%

    No Known Activations