© 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. 10-RES-JB
    11. 3413
    Prev
    Next
    INDEX
    Explanations

    phrases related to monetary rewards or penalties

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential limits or maximum values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.58
     Mistress
    -0.57
     Mate
    -0.57
     Abyss
    -0.57
     bitters
    -0.56
     Grimoire
    -0.55
     Narc
    -0.55
     Aliens
    -0.55
     Cele
    -0.54
     mistress
    -0.53
    POSITIVE LOGITS
    regulation
    1.12
    regulated
    1.05
    graded
    1.00
    grading
    1.00
    sized
    0.99
    grades
    0.99
    raised
    0.98
    votes
    0.96
    rights
    0.96
    dating
    0.94
    Activations Density 0.039%

    No Known Activations