© 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. 3-RES-JB
    11. 8902
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or communities

    oai_token-act-pair · gpt-3.5-turbo

    words related to communication and community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olkien
    -0.78
    BALL
    -0.74
    inning
    -0.70
    engeance
    -0.68
    avorite
    -0.64
     Slayer
    -0.63
    !/
    -0.62
    AGES
    -0.60
     rooting
    -0.60
    OPLE
    -0.59
    POSITIVE LOGITS
     commun
    1.28
    icator
    1.18
    icators
    1.16
    ique
    1.10
    icable
    1.07
    icol
    1.03
    icative
    0.97
    icip
    0.95
    iqu
    0.95
     Commun
    0.94
    Activations Density 0.006%

    No Known Activations