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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 5647
    Prev
    Next
    INDEX
    Explanations

    adjectives or adjectival phrases with strong connotations

    oai_token-act-pair · gpt-3.5-turbo

    expressions and phrases related to warnings or caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assemblies
    -0.81
     Norn
    -0.77
     Annotations
    -0.73
    ngth
    -0.71
    isine
    -0.71
    ancies
    -0.67
    atography
    -0.65
    ovies
    -0.64
    idas
    -0.63
    arettes
    -0.63
    POSITIVE LOGITS
     nightmare
    0.78
    leg
    0.74
    gap
    0.71
    kill
    0.68
    fest
    0.65
     tactic
    0.65
     deterrent
    0.64
    cat
    0.64
    con
    0.64
    take
    0.63
    Activations Density 0.473%

    No Known Activations