© 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. 7-RES-JB
    11. 3133
    Prev
    Next
    INDEX
    Explanations

    terms related to technical commands and information, possibly computer-related instructions

    oai_token-act-pair · gpt-3.5-turbo
    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
    Ö¼
    -0.73
    ¿½
    -0.70
    ĨĴ
    -0.67
    士
    -0.60
    ukong
    -0.59
     coli
    -0.58
    odiac
    -0.56
    infeld
    -0.56
    \\\\\\\\
    -0.55
    TEXTURE
    -0.54
    POSITIVE LOGITS
    sels
    0.68
     LLP
    0.65
    shed
    0.56
    utra
    0.55
    hers
    0.53
     pans
    0.51
    loe
    0.50
    lbs
    0.50
    inning
    0.50
    atoes
    0.49
    Activations Density 1.311%

    No Known Activations