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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19368
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to likes, such as "liked" or "likes"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of segment markers in the text

    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
    ãĥ¼ãĥĨãĤ£
    -0.70
     Rim
    -0.68
     Lit
    -0.65
     spirited
    -0.63
     Satanic
    -0.61
     Labor
    -0.61
     compensated
    -0.60
    éĹĺ
    -0.58
    ħĭ
    -0.58
     Debor
    -0.57
    POSITIVE LOGITS
    ayers
    1.35
    ocated
    1.30
    ateral
    1.30
    oyal
    1.28
    aptop
    1.27
    ifestyle
    1.27
    ibrarian
    1.25
    ongevity
    1.24
    aying
    1.22
    apsed
    1.21
    Activations Density 0.034%

    No Known Activations