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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 2858
    Prev
    Next
    INDEX
    Explanations

    numerical ranges or spans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ranges and combat-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Express
    -0.78
    uph
    -0.71
    Hub
    -0.69
    DVD
    -0.69
     Eaton
    -0.68
    cond
    -0.66
     Virgin
    -0.66
    cart
    -0.65
    express
    -0.65
     Couch
    -0.65
    POSITIVE LOGITS
     ranged
    3.39
     melee
    2.62
     Melee
    2.09
    ranged
    1.74
     projectile
    1.45
     projectiles
    1.37
     AoE
    1.28
     DPS
    1.25
    anged
    1.19
     Brawl
    1.10
    Activations Density 0.035%

    No Known Activations