© 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. 2-RES-JB
    11. 16118
    Prev
    Next
    INDEX
    Explanations

    references to technology products and features

    oai_token-act-pair · gpt-3.5-turbo

    references to anime

    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
    ky
    -0.83
    anic
    -0.81
    itary
    -0.77
    atorial
    -0.72
    arty
    -0.68
    rious
    -0.68
    oyd
    -0.68
    vor
    -0.66
    arsh
    -0.66
    ophical
    -0.65
    POSITIVE LOGITS
     thereof
    0.69
    ©¶æ
    0.66
    Factor
    0.64
     embassies
    0.62
    arest
    0.61
     fullest
    0.60
    Uncommon
    0.60
     subtitle
    0.60
    SAY
    0.59
     cleaners
    0.59
    Activations Density 0.000%

    No Known Activations