© 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. 7-RES-JB
    11. 11544
    Prev
    Next
    INDEX
    Explanations

    descriptions of individuals including their actions and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe individuals and their characteristics or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uta
    -0.75
    rency
    -0.74
    perty
    -0.66
    apest
    -0.66
    ats
    -0.65
    ombat
    -0.63
    dfx
    -0.63
    anyon
    -0.61
     COVER
    -0.60
    endas
    -0.60
    POSITIVE LOGITS
     eldest
    0.76
     youngest
    0.72
     graduated
    0.69
     surn
    0.68
     underwent
    0.67
    ãĤ©
    0.66
     devout
    0.64
     undergo
    0.64
     hailed
    0.64
     credited
    0.64
    Activations Density 0.206%

    No Known Activations