Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20136
    Prev
    Next
    INDEX
    Explanations

    section breaks in the text

    oai_token-act-pair · gpt-3.5-turbo

    indicators of statistical performance evaluations

    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
     popul
    -0.80
    ansk
    -0.78
     arte
    -0.76
    utic
    -0.76
     behaviour
    -0.74
     censored
    -0.74
     endeavour
    -0.74
     Vik
    -0.74
     censorship
    -0.73
    izoph
    -0.73
    POSITIVE LOGITS
    Players
    1.20
    ESPN
    1.14
    Dallas
    1.12
    sports
    1.10
    Detroit
    1.09
    Coach
    1.07
    NBA
    1.03
    Denver
    1.02
    QB
    1.02
    Miami
    1.02
    Activations Density 0.330%

    No Known Activations