© 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. 4-RES-JB
    11. 7477
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, titles, or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations, food items, and individuals

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

    No Comments

    Negative Logits
    ãĥ¥
    -0.79
    kees
    -0.75
    ocular
    -0.68
    £
    -0.66
    iltration
    -0.64
     allowance
    -0.61
    WAYS
    -0.60
     NHS
    -0.60
    ffen
    -0.60
    eral
    -0.59
    POSITIVE LOGITS
    aic
    0.89
    y
    0.88
    ments
    0.85
    spe
    0.79
    Ģ
    0.77
    sonian
    0.76
    ¯
    0.76
    teenth
    0.75
    pillar
    0.75
    ors
    0.74
    Activations Density 0.029%

    No Known Activations