Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7143
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Office"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of governmental or organizational offices

    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
    udeau
    -0.72
     worsh
    -0.69
    ubes
    -0.67
    oise
    -0.67
    hus
    -0.67
    nir
    -0.66
     Haram
    -0.65
    theless
    -0.64
    âķIJâķIJ
    -0.64
    itious
    -0.63
    POSITIVE LOGITS
     365
    0.84
    gur
    0.83
     Depot
    0.79
     Office
    0.75
     Desk
    0.72
     Personnel
    0.68
    person
    0.68
    osa
    0.66
     Paper
    0.66
    Office
    0.65
    Activations Density 0.028%

    No Known Activations