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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 10997
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the essence or critical point of a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional dependencies or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.78
    Semitic
    -0.77
    irens
    -0.76
    oqu
    -0.75
    sup
    -0.71
    ©¶æ
    -0.71
    ä
    -0.70
    atel
    -0.69
    cler
    -0.68
    ocry
    -0.68
    POSITIVE LOGITS
     patience
    1.18
     figuring
    1.13
     ensuring
    1.09
     mastering
    1.08
     remembering
    1.07
     luck
    1.03
     educating
    1.03
     recognizing
    1.02
     knowing
    1.02
     understanding
    0.99
    Activations Density 0.253%

    No Known Activations