© 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. 3885
    Prev
    Next
    INDEX
    Explanations

    email-related actions like "adding" or "registering."

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating an action of contribution or involvement

    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
     Pru
    -0.64
     fixme
    -0.64
     Shooter
    -0.64
     Fixes
    -0.62
     Thief
    -0.61
     Consent
    -0.60
     Dise
    -0.60
     Shogun
    -0.60
     Rider
    -0.58
     gon
    -0.58
    POSITIVE LOGITS
    ipl
    0.76
    ipple
    0.76
    OTOS
    0.69
    ilde
    0.69
    iland
    0.68
    APH
    0.66
    aft
    0.66
    hest
    0.65
    onz
    0.64
    ites
    0.64
    Activations Density 0.000%

    No Known Activations