© 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. 6798
    Prev
    Next
    INDEX
    Explanations

    words related to technical terms or gibberish phrases

    oai_token-act-pair · gpt-3.5-turbo

    special characters or placeholders

    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
    notes
    -0.76
    quished
    -0.75
    espie
    -0.71
    ingers
    -0.70
    bies
    -0.69
    idges
    -0.68
     trainers
    -0.67
    osures
    -0.66
    awaru
    -0.65
    assies
    -0.65
    POSITIVE LOGITS
    ĥ
    1.31
    ÏĦ
    1.12
    ½
    1.02
    Ĥ
    1.01
    κ
    0.99
    ε
    0.97
    ¼
    0.97
    Ëľ
    0.97
    Ī
    0.97
    Ùħ
    0.97
    Activations Density 0.006%

    No Known Activations