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. 4-RES-JB
    6. 18225
    Prev
    Next
    INDEX
    Explanations

    people's job titles and organizational roles

    oai_token-act-pair · gpt-3.5-turbo

    corporate titles and positions, especially related to vice presidents and directors

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

    No Comments

    Negative Logits
    soDeliveryDate
    -0.78
     pharmacies
    -0.69
     playbook
    -0.67
     foll
    -0.66
     plaus
    -0.66
     mug
    -0.65
    rants
    -0.64
    psons
    -0.63
    rified
    -0.63
    rists
    -0.63
    POSITIVE LOGITS
     Languages
    0.84
     Vir
    0.80
     overseeing
    0.78
     Operations
    0.76
     Leth
    0.71
     Yates
    0.71
     UNESCO
    0.70
     Ake
    0.70
     Sund
    0.69
     Alas
    0.69
    Activations Density 0.196%

    No Known Activations