© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8493
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements or updates

    oai_token-act-pair · gpt-3.5-turbo
    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
     restraint
    -0.73
    cair
    -0.71
    inished
    -0.66
     menace
    -0.65
    protection
    -0.65
    rouse
    -0.65
     undermines
    -0.64
    violence
    -0.63
    cit
    -0.62
     harms
    -0.62
    POSITIVE LOGITS
     pleased
    1.25
     thrilled
    1.18
     delighted
    1.17
     excited
    1.12
     glad
    1.09
     proud
    1.05
     releasing
    1.04
     thankful
    1.01
     hoping
    1.01
     planning
    1.00
    Activations Density 0.144%

    No Known Activations