© 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. 4-RES-JB
    11. 7395
    Prev
    Next
    INDEX
    Explanations

    phrases related to preferences or selections

    oai_token-act-pair · gpt-3.5-turbo

    words related to preferences and conditions affecting individuals or groups

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

    No Comments

    Negative Logits
    osaurs
    -0.91
    OPE
    -0.79
    izable
    -0.78
    apy
    -0.71
    ozo
    -0.70
     GOODMAN
    -0.69
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
    Accessory
    -0.69
    Reviewer
    -0.69
    IZE
    -0.69
    POSITIVE LOGITS
    erent
    1.16
    eren
    1.00
    lot
    0.90
    erences
    0.88
    ixed
    0.86
    elt
    0.85
    fw
    0.82
    liction
    0.79
    illed
    0.77
    raid
    0.76
    Activations Density 0.014%

    No Known Activations