© 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. 7-RES-JB
    11. 21080
    Prev
    Next
    INDEX
    Explanations

    phone numbers or technical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical or coded information, particularly in a technical context

    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
     wedd
    -0.70
     boarding
    -0.69
     til
    -0.65
     shells
    -0.63
    cheon
    -0.62
     bang
    -0.62
     lion
    -0.61
     lang
    -0.59
     boun
    -0.59
    culosis
    -0.58
    POSITIVE LOGITS
    024
    0.79
    200000
    0.78
    776
    0.76
    0
    0.73
     Centauri
    0.72
    920
    0.72
    small
    0.71
    800
    0.71
    200
    0.70
    237
    0.69
    Activations Density 0.116%

    No Known Activations