© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3277
    Prev
    Next
    INDEX
    Explanations

    pronouns or nouns related to personal or community belonging

    oai_token-act-pair · gpt-3.5-turbo

    references to maintaining or providing support for various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haps
    -0.75
    apego
    -0.67
    should
    -0.67
     ACTIONS
    -0.66
     =>
    -0.66
    asus
    -0.65
    icion
    -0.64
    ramid
    -0.64
    vernment
    -0.64
    DragonMagazine
    -0.64
    POSITIVE LOGITS
     afloat
    1.34
     alive
    1.32
     intact
    1.20
     accountable
    1.19
     safe
    1.02
     unchanged
    1.01
     solvent
    0.98
     untouched
    0.97
     guessing
    0.95
     quiet
    0.93
    Activations Density 0.124%

    No Known Activations