© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18732
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or countries

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to geographic origins and placements of entities or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assi
    -0.89
    lest
    -0.78
    most
    -0.77
     deserves
    -0.76
    fortunately
    -0.75
     Collider
    -0.75
    ŃĶ
    -0.72
    Synopsis
    -0.72
    enough
    -0.71
    hood
    -0.71
    POSITIVE LOGITS
     subsidiaries
    0.95
     Asians
    0.85
     males
    0.84
     Caucas
    0.80
     smaller
    0.80
     mainland
    0.79
     wealthier
    0.79
     females
    0.78
     women
    0.78
     concentrated
    0.77
    Activations Density 0.247%

    No Known Activations