© 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. 2-RES-JB
    11. 612
    Prev
    Next
    INDEX
    Explanations

    words or parts of words that contain the sequence "cos"

    oai_token-act-pair · gpt-4-turbo

    phrases related to the term "cosmos."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "cos" and its variations within contexts related to entertainment or sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.80
    OWN
    -0.66
     NOTICE
    -0.62
     warrants
    -0.62
     Pew
    -0.61
     Bedford
    -0.60
    OUT
    -0.60
    interstitial
    -0.59
     sentence
    -0.59
     Chamberlain
    -0.58
    POSITIVE LOGITS
    metic
    1.28
    metics
    1.25
    cos
    1.21
    mic
    1.00
    idon
    0.96
    mopolitan
    0.96
    atell
    0.96
     horizont
    0.94
    stal
    0.90
    mos
    0.89
    Activations Density 0.008%

    No Known Activations