© 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. 1-RES-JB
    11. 6644
    Prev
    Next
    INDEX
    Explanations

    negative terms related to exclusion or control

    oai_token-act-pair · gpt-3.5-turbo

    terms related to worship and disenfranchisement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    master
    -0.77
    SHIP
    -0.75
    buster
    -0.75
     Maid
    -0.71
    wolf
    -0.70
     Blow
    -0.70
     Dragonbound
    -0.70
     Force
    -0.69
     Consent
    -0.67
    WER
    -0.67
    POSITIVE LOGITS
    aded
    1.06
    icably
    0.97
    odied
    0.96
    ading
    0.96
    oby
    0.93
    izoph
    0.92
    itting
    0.91
    asion
    0.91
    acqu
    0.91
    anging
    0.91
    Activations Density 0.040%

    No Known Activations