© 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. 13326
    Prev
    Next
    INDEX
    Explanations

    phrases indicating permission or options

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or possibilities related to user actions

    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
     Fighter
    -0.64
    sett
    -0.62
     Oss
    -0.60
     Interior
    -0.59
    sein
    -0.59
    ãĥ¼ãĥ«
    -0.58
     Ori
    -0.57
     Rahman
    -0.57
    agic
    -0.56
     Cav
    -0.56
    POSITIVE LOGITS
    haps
    1.15
    hap
    0.99
     optionally
    0.97
     choose
    0.86
    onna
    0.84
     elect
    0.84
    bes
    0.81
    merce
    0.75
     enter
    0.75
    ghai
    0.74
    Activations Density 0.049%

    No Known Activations