© 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. 8-RES-JB
    11. 20278
    Prev
    Next
    INDEX
    Explanations

    terms related to weapons and combat

    oai_token-act-pair · gpt-3.5-turbo

    names of magical creatures or supernatural entities in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nodd
    -0.78
    soDeliveryDate
    -0.78
     licens
    -0.75
     certific
    -0.74
     sitcom
    -0.73
    internet
    -0.71
     booking
    -0.71
     referen
    -0.70
    eatures
    -0.70
     advertisers
    -0.68
    POSITIVE LOGITS
    bane
    1.17
    blade
    1.10
     Armor
    1.05
     Cooldown
    1.04
     Paladin
    1.04
     Mastery
    1.04
     Cloak
    1.03
     Totem
    1.02
     Golem
    1.00
     Potion
    0.99
    Activations Density 0.213%

    No Known Activations