© 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. 22953
    Prev
    Next
    INDEX
    Explanations

    words related to emotions or behaviors associated with being calm or composed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "calm" and related sentiments

    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
    ographies
    -0.78
    OGR
    -0.73
    rocket
    -0.71
    hester
    -0.68
    ammy
    -0.68
    alez
    -0.67
    paralle
    -0.65
    alian
    -0.65
    raped
    -0.64
    iosyncr
    -0.63
    POSITIVE LOGITS
    ness
    1.04
     calm
    1.01
     demeanor
    0.98
    est
    0.83
     composure
    0.81
     tranquil
    0.79
    ament
    0.77
    hearted
    0.77
     calming
    0.76
     bree
    0.75
    Activations Density 0.031%

    No Known Activations