© 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. 11-RES-JB
    11. 7174
    Prev
    Next
    INDEX
    Explanations

    references to the word "fish" and related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MSI
    -0.69
     Canter
    -0.65
    xus
    -0.63
     AMC
    -0.63
    Madison
    -0.60
     Machina
    -0.59
    rian
    -0.58
    FINE
    -0.58
    verend
    -0.58
     Citizens
    -0.57
    POSITIVE LOGITS
    bowl
    1.46
    mong
    1.28
    hook
    1.23
    nets
    1.20
    tails
    1.14
    tail
    1.13
    meal
    1.11
    tailed
    1.10
    bone
    1.05
    tank
    1.02
    Activations Density 0.048%

    No Known Activations