© 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. 6-RES-JB
    11. 15512
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases or compounds

    oai_token-act-pair · gpt-3.5-turbo

    negative references to "day-to-day" experiences or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aborted
    -0.70
     McKin
    -0.65
     Seym
    -0.63
     Viper
    -0.63
     laure
    -0.62
     Corpus
    -0.62
     Coat
    -0.60
    Ĥª
    -0.60
     Tempest
    -0.59
     tuning
    -0.58
    POSITIVE LOGITS
    morrow
    0.88
    date
    0.88
    advertising
    0.84
    earth
    0.84
    arms
    0.84
    sale
    0.83
    reach
    0.83
    equ
    0.83
    order
    0.82
    learn
    0.81
    Activations Density 0.029%

    No Known Activations