© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14088
    Prev
    Next
    INDEX
    Explanations

    generic statements or press releases structured with a certain format

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "by," indicating attribution or authorship

    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
    ashtra
    -0.94
    ivia
    -0.84
    itialized
    -0.71
    hene
    -0.70
    acci
    -0.69
    uality
    -0.68
    gregation
    -0.68
    ulnerable
    -0.68
    çͰ
    -0.68
    ratom
    -0.66
    POSITIVE LOGITS
     Xin
    0.72
     virtue
    0.68
     UID
    0.64
    laws
    0.64
     courier
    0.63
     Blizzard
    0.63
     Nay
    0.63
     Dish
    0.62
    products
    0.62
     Wizards
    0.62
    Activations Density 0.090%

    No Known Activations