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. 0-RES-JB
    6. 3186
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to the action of reaching

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reaching"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ston
    -0.69
    resses
    -0.66
    old
    -0.62
    ublic
    -0.61
    ress
    -0.60
    Boo
    -0.60
    ophobia
    -0.60
    Assistant
    -0.59
    ety
    -0.59
    olph
    -0.59
    POSITIVE LOGITS
     reaching
    3.32
     reach
    1.96
    reaching
    1.86
     reaches
    1.72
     reached
    1.71
     achieving
    1.66
     hitting
    1.51
     contacting
    1.44
     exceeding
    1.37
     approaching
    1.36
    Activations Density 0.012%

    No Known Activations