© 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. 14858
    Prev
    Next
    INDEX
    Explanations

    organizations and associations related to various fields

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to organizations and their representatives

    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
    Pg
    -0.68
    ãģĤ
    -0.65
    Ü
    -0.64
    ãĥİ
    -0.63
     scissors
    -0.62
    expression
    -0.62
     tantal
    -0.61
    pmwiki
    -0.61
     recess
    -0.60
     diluted
    -0.60
    POSITIVE LOGITS
     fame
    1.00
     told
    0.84
     (@
    0.75
     tells
    0.74
     testified
    0.69
    ?,
    0.69
     says
    0.69
     commented
    0.68
    onica
    0.67
     said
    0.65
    Activations Density 0.327%

    No Known Activations