© 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. 0-RES-JB
    11. 16730
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "key" often associated with names or technical use rather than the physical object

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the term "key"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gleaming
    -0.71
     dispers
    -0.67
     Olymp
    -0.65
     Continued
    -0.65
     interstellar
    -0.65
     discharge
    -0.64
     bene
    -0.64
     Bett
    -0.64
    URES
    -0.63
     course
    -0.61
    POSITIVE LOGITS
    key
    4.31
    keys
    2.95
    KEY
    2.53
    Key
    2.32
    Keys
    1.67
     Key
    1.67
     KEY
    1.63
     key
    1.57
     keys
    1.45
     Keys
    1.27
    Activations Density 0.018%

    No Known Activations