© 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. 2874
    Prev
    Next
    INDEX
    Explanations

    locations or directions within a physical space

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to exploration and discovery in a game setting

    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
    professional
    -0.82
    Professional
    -0.82
    aughs
    -0.77
     Daly
    -0.73
     professionalism
    -0.72
     Fitzpatrick
    -0.72
     ÂŃ
    -0.71
     Baldwin
    -0.71
    review
    -0.70
    Liberal
    -0.70
    POSITIVE LOGITS
     dungeons
    1.54
     caves
    1.53
     respawn
    1.46
     NPCs
    1.43
     spawns
    1.43
     tunnels
    1.41
     traps
    1.40
     teleport
    1.39
     chests
    1.34
     quests
    1.33
    Activations Density 0.497%

    No Known Activations