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. 1-RES-JB
    6. 8489
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology or software

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "am" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mississ
    -0.72
    theless
    -0.71
     Durham
    -0.71
     Titanic
    -0.68
    Tang
    -0.66
     externalToEVAOnly
    -0.66
     Moons
    -0.65
     corners
    -0.65
    culosis
    -0.64
     Dough
    -0.63
    POSITIVE LOGITS
    sterdam
    1.14
    ateurs
    1.07
    azon
    1.05
    ethyst
    1.02
     am
    0.93
    assing
    0.93
    ajor
    0.89
    icus
    0.89
    abella
    0.87
    oen
    0.87
    Activations Density 0.020%

    No Known Activations