© 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. 23908
    Prev
    Next
    INDEX
    Explanations

    Italian names, particularly with the suffix "-iano"

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific names, particularly those of notable individuals

    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
    ivities
    -0.94
    stones
    -0.85
    mable
    -0.84
    matically
    -0.84
    ipeg
    -0.82
    bread
    -0.79
    drawn
    -0.79
    tags
    -0.78
    rity
    -0.77
    pring
    -0.76
    POSITIVE LOGITS
    zzi
    1.45
    ÄŁ
    1.22
     Rossi
    0.99
    jo
    0.97
    vernment
    0.95
    zzo
    0.94
    zza
    0.89
    ctor
    0.86
     Duterte
    0.85
    ahu
    0.83
    Activations Density 0.090%

    No Known Activations