© 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. 17160
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter 'J' followed by a name or title

    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
    holders
    -0.92
    holder
    -0.78
     Rebels
    -0.65
     captcha
    -0.65
     diapers
    -0.65
     Growing
    -0.62
     Anthem
    -0.61
     Soviets
    -0.61
     pony
    -0.60
     galleries
    -0.60
    POSITIVE LOGITS
    igsaw
    1.27
    ealous
    1.25
    upiter
    1.19
    ourn
    1.18
    itsu
    1.17
    umbo
    1.15
    ournals
    1.13
    umper
    1.11
    okes
    1.09
    ohan
    1.09
    Activations Density 0.034%

    No Known Activations