© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6093
    Prev
    Next
    INDEX
    Explanations

    keywords related to special skills or powers, like spells, abilities, perks, racial abilities, and passive boosts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to abilities and their various attributes

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

    No Comments

    Negative Logits
    isle
    -0.83
    76561
    -0.73
     Lions
    -0.70
    oglu
    -0.67
    obar
    -0.66
    orld
    -0.66
     Romero
    -0.65
    ardy
    -0.65
     Dover
    -0.65
     Indies
    -0.65
    POSITIVE LOGITS
     abilities
    0.96
     descriptions
    0.82
     cooldown
    0.79
    Cooldown
    0.77
    BILITIES
    0.77
     description
    0.77
     mastered
    0.76
     bestowed
    0.76
    linger
    0.74
     conferred
    0.74
    Activations Density 0.049%

    No Known Activations