© 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. 3-RES-JB
    11. 5111
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs suggesting a strong or emphatic sentiment

    oai_token-act-pair · gpt-3.5-turbo

    words related to strong approval or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itism
    -0.78
    perature
    -0.78
     skelet
    -0.77
    ipeg
    -0.71
    agara
    -0.71
    nery
    -0.70
    inki
    -0.69
    aho
    -0.67
    adan
    -0.66
    esty
    -0.65
    POSITIVE LOGITS
    oslav
    0.99
    OUND
    0.88
    soType
    0.74
    rued
    0.74
    onent
    0.74
    ounded
    0.73
    Hung
    0.69
    Lens
    0.69
    ounding
    0.69
    Rect
    0.67
    Activations Density 0.011%

    No Known Activations