© 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. 797
    Prev
    Next
    INDEX
    Explanations

    technical terms related to various fields such as technology, sports, and law

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and product announcements

    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
     contag
    -0.64
     traps
    -0.62
     impede
    -0.60
     clutter
    -0.59
     redund
    -0.57
     plague
    -0.56
     urgency
    -0.56
     cleanup
    -0.56
     temptation
    -0.55
     scram
    -0.55
    POSITIVE LOGITS
    éĥ
    0.76
    代
    0.75
    AAAAAAAA
    0.71
    ÃĥÃĤÃĥÃĤ
    0.71
    =-=-=-=-
    0.70
    ONSORED
    0.70
    boro
    0.67
    Legend
    0.66
    !!!!
    0.66
    reciation
    0.65
    Activations Density 1.121%

    No Known Activations