© 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. 3-RES-JB
    11. 7168
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns referring to fantasy or imagination

    oai_token-act-pair · gpt-3.5-turbo

    the word "fantastic" and its variations, as well as terms related to fantasy and exploration

    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
    çĽ
    -0.70
    Kings
    -0.67
    mit
    -0.66
    Accessory
    -0.65
    DEN
    -0.65
    guard
    -0.62
     Elk
    -0.62
    keeper
    -0.61
    ership
    -0.61
     Cue
    -0.61
    POSITIVE LOGITS
    astical
    1.49
    astically
    1.39
    asia
    1.12
    ancies
    1.05
    imes
    0.95
    ão
    0.94
    agraph
    0.94
    inations
    0.94
    emis
    0.94
    abul
    0.92
    Activations Density 0.014%

    No Known Activations