© 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. 10-RES-JB
    11. 12719
    Prev
    Next
    INDEX
    Explanations

    words related to controversial or critical situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authority and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à©
    -0.68
     Amendments
    -0.67
     Typhoon
    -0.65
     Hok
    -0.61
     Amendment
    -0.59
    advertising
    -0.59
     Crunch
    -0.59
     Virt
    -0.59
     Provision
    -0.58
     Wind
    -0.58
    POSITIVE LOGITS
    cause
    1.11
     wise
    1.07
    ecause
    0.99
    ilaterally
    0.97
    matically
    0.96
    rily
    0.94
    lessly
    0.91
    wise
    0.84
    ically
    0.82
    ifies
    0.81
    Activations Density 0.496%

    No Known Activations