© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16205
    Prev
    Next
    INDEX
    Explanations

    words related to media outlets or publications

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "mag" in various contexts, indicating a focus on magazine-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELL
    -0.66
     registered
    -0.63
    ãģį
    -0.61
     Hastings
    -0.61
     Assassins
    -0.60
     typed
    -0.59
     Reaper
    -0.59
     VIDE
    -0.58
    eed
    -0.58
     Pric
    -0.58
    POSITIVE LOGITS
    azine
    1.53
    netic
    1.51
    azines
    1.23
    mag
    1.22
    ikarp
    1.13
    istrate
    1.11
    istrates
    1.08
    dinand
    1.07
    nesium
    0.99
    ical
    0.98
    Activations Density 0.008%

    No Known Activations