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. 3-RES-JB
    6. 11155
    Prev
    Next
    INDEX
    Explanations

    verbs related to presenting or promoting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pitch" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iliary
    -0.83
    tesy
    -0.83
    illard
    -0.76
    guard
    -0.71
    inals
    -0.68
    avis
    -0.68
    arts
    -0.68
    isms
    -0.67
    guards
    -0.66
    aspx
    -0.64
    POSITIVE LOGITS
     pitched
    1.13
     pitch
    1.12
     pitches
    0.98
     Pitch
    0.89
     pitching
    0.88
    fork
    0.84
     tents
    0.81
    odcast
    0.73
    roth
    0.67
     Hut
    0.66
    Activations Density 0.010%

    No Known Activations