© 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. 11-RES-JB
    11. 21114
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or tasks involving change, adaptation, or solution-finding

    oai_token-act-pair · gpt-3.5-turbo

    actions related to influencing, supporting, or changing situations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    noon
    -0.73
     AND
    -0.68
     Located
    -0.64
    tick
    -0.59
    Enlarge
    -0.59
    ixty
    -0.59
    utenberg
    -0.59
    oiler
    -0.58
    âĻ¦
    -0.58
     Dragonbound
    -0.57
    POSITIVE LOGITS
     them
    1.05
     others
    0.99
     alliances
    0.83
     their
    0.81
     agendas
    0.79
     other
    0.78
     oneself
    0.75
     accordingly
    0.74
     friendships
    0.73
     punishments
    0.73
    Activations Density 0.475%

    No Known Activations