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. 0-RES-JB
    6. 974
    Prev
    Next
    INDEX
    Explanations

    website URLs or numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers or codes, particularly in a structured data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sav
    -0.82
     Sim
    -0.78
     Malt
    -0.76
     Manziel
    -0.74
     Virgin
    -0.74
     Isa
    -0.72
     Rand
    -0.70
     whisky
    -0.69
     Madagascar
    -0.69
    isman
    -0.69
    POSITIVE LOGITS
    303
    1.94
    404
    1.88
    204
    1.86
    202
    1.85
    604
    1.84
    203
    1.83
    302
    1.81
    403
    1.79
    503
    1.77
    402
    1.74
    Activations Density 0.047%

    No Known Activations