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. 10-RES-JB
    6. 383
    Prev
    Next
    INDEX
    Explanations

    keywords related to pushing, pressing, or advocating for a particular action or outcome

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "press" and its variants associated with influence or pressure in a political context

    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
    ateur
    -0.91
    /-
    -0.78
    oxide
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.71
    eye
    -0.68
    Untitled
    -0.66
    Condition
    -0.66
    psons
    -0.65
    ateurs
    -0.65
    namese
    -0.64
    POSITIVE LOGITS
     forward
    1.13
     ahead
    1.05
     onward
    0.96
     harder
    0.92
     toward
    0.84
     legislators
    0.83
     forwards
    0.83
     boundaries
    0.82
     through
    0.82
     lawmakers
    0.81
    Activations Density 0.071%

    No Known Activations