© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3255
    Prev
    Next
    INDEX
    Explanations

    words related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns or names related to trends and popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [*]
    -0.89
     Heard
    -0.82
     Fif
    -0.82
     Idaho
    -0.81
     IST
    -0.77
    ãģĦ
    -0.77
     Kits
    -0.74
    Kit
    -0.71
     Katie
    -0.71
     Idle
    -0.69
    POSITIVE LOGITS
    ra
    1.63
    ro
    1.42
    ras
    1.42
    ran
    1.41
    roth
    1.36
    ror
    1.35
    roc
    1.31
    rov
    1.31
    rag
    1.31
    ron
    1.31
    Activations Density 0.151%

    No Known Activations