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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6255
    Prev
    Next
    INDEX
    Explanations

    people's professions or expertise

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and their professions or roles

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

    No Comments

    Negative Logits
    ħĭ
    -0.67
    Ĥİ
    -0.66
    osponsors
    -0.62
    tails
    -0.59
    azeera
    -0.59
    inations
    -0.58
     ultras
    -0.57
     VIDEOS
    -0.57
    dos
    -0.57
    Ire
    -0.56
    POSITIVE LOGITS
     combining
    0.74
     consisting
    0.67
    rette
    0.65
     assemb
    0.64
     combines
    0.62
     comprised
    0.59
     spanning
    0.58
     encomp
    0.56
     blends
    0.56
     circa
    0.55
    Activations Density 0.648%

    No Known Activations