© 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. 10-RES-JB
    11. 14113
    Prev
    Next
    INDEX
    Explanations

    academic and analytical language related to discussing various topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    discussions and references to arguments or narratives related to claims and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poon
    -0.68
    Interstitial
    -0.64
    +.
    -0.64
    ECA
    -0.60
    Had
    -0.60
    Rated
    -0.59
    ãĤ¼
    -0.59
    otonin
    -0.59
     guiActiveUnfocused
    -0.58
    âĹ¼
    -0.58
    POSITIVE LOGITS
     seems
    1.08
     arises
    1.07
     begs
    1.03
     varies
    1.03
     begins
    1.01
     boils
    1.01
     assumes
    0.99
     revolves
    0.99
     illustrates
    0.99
     differs
    0.98
    Activations Density 0.243%

    No Known Activations