© 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. 2-RES-JB
    11. 12031
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the name "Bush" or similar spellings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ush" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     occup
    -0.69
     stake
    -0.69
     recomm
    -0.68
     permit
    -0.66
     peer
    -0.65
     stakes
    -0.65
    İĭ
    -0.62
     march
    -0.62
     dimensional
    -0.62
     substituted
    -0.62
    POSITIVE LOGITS
    ush
    1.19
    ivas
    0.99
    ORTS
    0.92
    annah
    0.91
    adow
    0.86
    rooms
    0.85
    trap
    0.82
    adows
    0.82
     Leopard
    0.81
    kat
    0.79
    Activations Density 0.004%

    No Known Activations