© 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. 20307
    Prev
    Next
    INDEX
    Explanations

    words related to actions or attributes that involve intelligence, skill, or interactivity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to skills, creativity, and inventions

    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
     Kov
    -0.60
    asus
    -0.60
    Args
    -0.57
    âĸ¬
    -0.57
    ]'
    -0.57
    Õ
    -0.56
    ERAL
    -0.56
    \\\\\\\\
    -0.55
    \\\\\\\\\\\\\\\\
    -0.55
    ALLY
    -0.54
    POSITIVE LOGITS
    cape
    1.22
    heet
    1.22
    mith
    1.18
    cale
    1.18
    pring
    1.08
    pace
    1.06
    paces
    1.05
    creen
    1.04
    hare
    1.04
    peed
    1.03
    Activations Density 0.420%

    No Known Activations