© 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. 9-RES-JB
    11. 5990
    Prev
    Next
    INDEX
    Explanations

    phrases related to broadcasting networks

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oro
    -0.84
    Downloadha
    -0.79
     Frankenstein
    -0.68
    ICAN
    -0.64
     Uriel
    -0.64
     Hugo
    -0.61
     Guerrero
    -0.61
     Canaver
    -0.59
     Minerva
    -0.59
     bitters
    -0.58
    POSITIVE LOGITS
    casters
    1.27
    casting
    1.17
    bent
    1.17
    band
    1.14
    caster
    1.12
    sheet
    1.11
    sword
    1.10
    casts
    1.09
    ening
    1.03
    sided
    1.02
    Activations Density 0.022%

    No Known Activations