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. 8-RES-JB
    6. 12028
    Prev
    Next
    INDEX
    Explanations

    words related to pushing or striving towards a goal

    oai_token-act-pair · gpt-3.5-turbo

    recurring instances of the word "push" and its variations to indicate advocacy or pressure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lys
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.70
    atural
    -0.69
    ateur
    -0.65
    brance
    -0.65
    obyl
    -0.63
    eye
    -0.63
    ruct
    -0.62
    psons
    -0.62
    liest
    -0.62
    POSITIVE LOGITS
     forward
    1.12
     ahead
    0.97
     boundaries
    0.96
     onward
    0.94
     toward
    0.92
     towards
    0.87
     forwards
    0.84
     forth
    0.81
     aside
    0.81
     harder
    0.80
    Activations Density 0.058%

    No Known Activations