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. 7-RES-JB
    6. 3317
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    names, particularly those of people, locations, and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢ
    -0.85
    士
    -0.83
     Confederation
    -0.76
    SPONSORED
    -0.69
    tics
    -0.66
    emies
    -0.65
    culosis
    -0.64
    ãĥŁ
    -0.63
    FORMATION
    -0.61
     Pradesh
    -0.61
    POSITIVE LOGITS
    heny
    0.77
    zinski
    0.71
    buck
    0.69
    dry
    0.68
    shall
    0.67
    onson
    0.67
    hof
    0.66
    aney
    0.66
     answ
    0.66
    ullivan
    0.65
    Activations Density 0.164%

    No Known Activations