© 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. 2-RES-JB
    11. 11986
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly the name "Fasching"

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to specific individuals, particularly in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingly
    -0.76
    ardless
    -0.69
    stakes
    -0.65
     Trojan
    -0.64
     Matth
    -0.62
    ATTLE
    -0.61
    esters
    -0.61
    hovah
    -0.60
    een
    -0.60
     Cheryl
    -0.60
    POSITIVE LOGITS
     Fas
    1.09
    uras
    0.86
    olina
    0.81
    arus
    0.80
    odic
    0.80
    emia
    0.78
    aun
    0.78
    idian
    0.78
    llan
    0.76
     feas
    0.76
    Activations Density 0.013%

    No Known Activations