© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 21334
    Prev
    Next
    INDEX
    Explanations

    specific verbs that describe a specialized skill or activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight areas of specialization or expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ---------
    -0.77
    forth
    -0.74
    runner
    -0.69
    mar
    -0.67
     Bagg
    -0.67
    down
    -0.66
    onel
    -0.66
    borne
    -0.66
    fm
    -0.64
    à¥
    -0.64
    POSITIVE LOGITS
     specialize
    1.17
     specialized
    1.11
     specializes
    1.08
     specializing
    0.87
     specialization
    0.86
    ategory
    0.86
     expertise
    0.83
     locality
    0.80
     specialty
    0.79
     specialists
    0.78
    Activations Density 0.019%

    No Known Activations