© 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. 6432
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive feedback or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    positive expressions of opinions or preferences

    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
    iliated
    -0.66
    å°Ĩ
    -0.65
     probable
    -0.63
    Registered
    -0.60
    interrupted
    -0.59
    iped
    -0.58
    WARE
    -0.58
     lethal
    -0.57
    bia
    -0.57
    udder
    -0.56
    POSITIVE LOGITS
     because
    0.94
     tho
    0.91
     bec
    0.77
    !!!!
    0.75
     though
    0.73
    cause
    0.72
     uncond
    0.71
    !!!!!!!!
    0.70
    !!!
    0.70
     :-)
    0.68
    Activations Density 0.613%

    No Known Activations