© 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 EvalsExportsinterp-engineNEWAPI 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. 4280
    Prev
    Next
    INDEX
    Explanations

    references to actions or intentions involving people, such as using digital wallets or supporting projects

    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
     apologies
    -0.69
    ãĥ´ãĤ¡
    -0.69
     suspensions
    -0.67
    è£
    -0.67
    ãĥķãĤ©
    -0.67
     deficit
    -0.65
     deficits
    -0.65
    pause
    -0.63
     depressing
    -0.63
     euphem
    -0.62
    POSITIVE LOGITS
     participate
    1.21
     participating
    1.10
     subscribing
    1.03
     participated
    1.01
     join
    0.99
     Particip
    0.97
     partake
    0.94
     participates
    0.94
     avail
    0.94
     enroll
    0.93
    Activations Density 0.590%

    No Known Activations