© 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. 7-RES-JB
    11. 23032
    Prev
    Next
    INDEX
    Explanations

    game terminology related to abilities and effects

    oai_token-act-pair · gpt-3.5-turbo

    game mechanics and abilities related to character stats and effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ°
    -0.94
    ajor
    -0.79
    ylum
    -0.77
    sonian
    -0.76
    Reviewer
    -0.76
    ovie
    -0.76
     Draper
    -0.75
    é¾įå
    -0.73
    ropolitan
    -0.71
    eday
    -0.70
    POSITIVE LOGITS
     cooldown
    1.46
     Cooldown
    1.40
    Cooldown
    1.21
     Healing
    1.19
     Damage
    1.18
     projectiles
    1.16
     melee
    1.15
     damage
    1.14
    damage
    1.14
     healing
    1.14
    Activations Density 0.255%

    No Known Activations