© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2214
    Prev
    Next
    INDEX
    Explanations

    phrases related to speaking out or expressing opinions assertively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "speak out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.76
     Jackets
    -0.71
    atomic
    -0.66
    ipment
    -0.64
     Metallic
    -0.63
     refresh
    -0.60
    GI
    -0.60
     mun
    -0.59
     Devils
    -0.58
     Ghosts
    -0.58
    POSITIVE LOGITS
     against
    1.05
     forcefully
    1.02
     loudly
    0.97
     louder
    0.90
     loud
    0.88
    against
    0.83
    rage
    0.81
     boldly
    0.80
     publicly
    0.78
     anonymously
    0.78
    Activations Density 0.042%

    No Known Activations