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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    6. 5050
    Prev
    Next
    INDEX
    Explanations

    phrases related to areas of expertise or concern

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight areas of expertise or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActive
    -0.89
    ivan
    -0.74
    BILL
    -0.70
    aired
    -0.69
    aciously
    -0.69
     Advertisement
    -0.69
    uters
    -0.68
     sqor
    -0.66
     Picks
    -0.65
     externalToEVAOnly
    -0.64
    POSITIVE LOGITS
     expertise
    1.17
     interest
    1.06
     specialization
    1.02
     weakness
    0.98
     concern
    0.95
     contention
    0.95
     overlap
    0.95
     competence
    0.94
     excellence
    0.91
     Excellence
    0.89
    Activations Density 0.125%

    No Known Activations