© 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. 8-RES-JB
    11. 2547
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals, particularly those with the initial 'K'

    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
    ashtra
    -1.00
    Ö¼
    -0.91
    REL
    -0.78
    »Ĵ
    -0.75
     Pwr
    -0.70
    BLIC
    -0.69
    INAL
    -0.66
    allic
    -0.66
     Vend
    -0.65
    IUM
    -0.65
    POSITIVE LOGITS
    ĸļ
    0.81
    isner
    0.70
    iffin
    0.69
    izabeth
    0.63
    unic
    0.62
     Oswald
    0.62
    flo
    0.62
    redo
    0.61
    hardt
    0.60
    eper
    0.59
    Activations Density 0.317%

    No Known Activations