© 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. 14290
    Prev
    Next
    INDEX
    Explanations

    characters such as symbols and specific names

    oai_token-act-pair · gpt-3.5-turbo

    special characters and formatting indicators

    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
    ividual
    -0.64
    halla
    -0.46
    gins
    -0.44
    idth
    -0.41
    ebted
    -0.40
    itton
    -0.39
     lasted
    -0.39
    okane
    -0.39
    ittal
    -0.38
    issance
    -0.38
    POSITIVE LOGITS
    76561
    0.52
     AAP
    0.46
     WATCHED
    0.42
    RESULTS
    0.39
    ËĪ
    0.39
    CVE
    0.38
    DATA
    0.38
    ï¸ı
    0.37
    /+
    0.37
     Pwr
    0.36
    Activations Density 2.569%

    No Known Activations