© 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. 4-RES-JB
    11. 6224
    Prev
    Next
    INDEX
    Explanations

    people's names, likely focusing on historical or academic figures

    oai_token-act-pair · gpt-3.5-turbo

    words related to historical or notable figures, particularly focusing on their names and attributes

    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
    yip
    -0.77
    jri
    -0.73
     anonym
    -0.66
     Mehran
    -0.63
     elev
    -0.63
     indebted
    -0.62
    Downloadha
    -0.61
     autonom
    -0.61
    terson
    -0.60
    arching
    -0.60
    POSITIVE LOGITS
    å°Ĩ
    0.89
     Fields
    0.69
    ale
    0.67
    itely
    0.67
     Gate
    0.66
    MAS
    0.66
    fell
    0.64
     Lowell
    0.63
    atorium
    0.62
    çĶŁ
    0.61
    Activations Density 0.212%

    No Known Activations