© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13312
    Prev
    Next
    INDEX
    Explanations

    prompts for engagement and opinions

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to hearing, seeing, and being, indicating a focus on sensory perception and existence

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

    No Comments

    Negative Logits
     aided
    -0.63
     signs
    -0.63
     Runes
    -0.62
     rails
    -0.59
    hari
    -0.58
    asca
    -0.58
     Sched
    -0.58
     brackets
    -0.58
     guiActiveUn
    -0.57
    ABC
    -0.56
    POSITIVE LOGITS
    uate
    0.80
     FANTASY
    0.74
    anything
    0.71
    ãĥ¤
    0.67
    GBT
    0.67
    venge
    0.66
    uctions
    0.66
    ãĥķãĤ©
    0.63
    ãĤ¦
    0.62
    thood
    0.62
    Activations Density 0.144%

    No Known Activations