© 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. 1-RES-JB
    11. 3096
    Prev
    Next
    INDEX
    Explanations

    the word "icular" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to vehicular topics and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibrary
    -0.90
    DVD
    -0.72
     Instruments
    -0.71
    izu
    -0.68
    eem
    -0.68
     [|
    -0.66
    uve
    -0.65
    itud
    -0.65
    ources
    -0.62
    Marginal
    -0.62
    POSITIVE LOGITS
    aredevil
    0.73
     skelet
    0.68
    uckland
    0.65
     Beir
    0.64
    quartered
    0.64
    joining
    0.64
    ©¶æ
    0.62
    justice
    0.62
    population
    0.61
     overwhelmed
    0.60
    Activations Density 0.000%

    No Known Activations