© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 13986
    Prev
    Next
    INDEX
    Explanations

    financial terms and numbers

    oai_token-act-pair · gpt-3.5-turbo

    the presence of unusual characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     segreg
    -0.72
     mans
    -0.70
     levers
    -0.68
     Unic
    -0.68
     guiActiveUnfocused
    -0.68
     tremend
    -0.67
     Phant
    -0.64
     Gan
    -0.62
     dividing
    -0.62
     menstru
    -0.62
    POSITIVE LOGITS
    ľ
    1.00
    £
    0.92
    º
    0.89
    ¬
    0.84
    Ľ
    0.84
    ¦
    0.84
    ¡
    0.83
    ¼
    0.79
    dro
    0.79
    Ń
    0.78
    Activations Density 0.309%

    No Known Activations