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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 21765
    Prev
    Next
    INDEX
    Explanations

    academic affiliations, particularly university names

    oai_token-act-pair · gpt-3.5-turbo

    references to universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elist
    -0.71
    serving
    -0.63
     bubbles
    -0.63
     trustworthy
    -0.61
    artisan
    -0.60
     sheets
    -0.60
    ãĥķãĤ©
    -0.60
    gone
    -0.60
    BACK
    -0.59
    downs
    -0.59
    POSITIVE LOGITS
     College
    0.96
     Extension
    0.92
    uates
    0.88
     Grants
    0.87
     Hospital
    0.87
     Athletic
    0.84
     Libraries
    0.82
     Faculty
    0.81
    Hum
    0.81
     Registrar
    0.81
    Activations Density 0.035%

    No Known Activations