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. 3-RES-JB
    6. 2126
    Prev
    Next
    INDEX
    Explanations

    references to the Electronic Frontier Foundation (EFF)

    oai_token-act-pair · gpt-3.5-turbo

    references to the Electronic Frontier Foundation (EFF)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gorge
    -0.83
    croft
    -0.76
     Wolves
    -0.70
     Redemption
    -0.69
     Britann
    -0.66
     Passenger
    -0.65
     Qt
    -0.65
     Ramsay
    -0.63
     Columbus
    -0.62
     Muller
    -0.61
    POSITIVE LOGITS
    IRED
    1.10
    ECT
    1.07
     EFF
    1.03
    ILY
    0.96
    ionage
    0.93
    EFF
    0.92
    ENSE
    0.87
    endi
    0.87
    ICE
    0.84
    DEF
    0.83
    Activations Density 0.008%

    No Known Activations