© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24321
    Prev
    Next
    INDEX
    Explanations

    words related to manifestation or emergence

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to emotional and social distress

    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
    FN
    -0.70
    byter
    -0.70
    MQ
    -0.69
    ivably
    -0.67
    oat
    -0.66
    racuse
    -0.66
    JR
    -0.66
    DB
    -0.65
     Codex
    -0.64
    recomm
    -0.63
    POSITIVE LOGITS
     manifested
    1.06
     dissip
    1.02
     subconscious
    0.88
     contagious
    0.85
     perme
    0.85
     haunting
    0.85
     outweigh
    0.83
     latent
    0.83
     lodged
    0.83
     extinguished
    0.83
    Activations Density 0.690%

    No Known Activations