© 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. 4-RES-JB
    11. 20890
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "den" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "den" in various contexts

    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
    cffffcc
    -0.77
    ramid
    -0.76
    lda
    -0.71
    Reply
    -0.70
    lihood
    -0.68
    EED
    -0.65
    avorite
    -0.65
    ullivan
    -0.64
    rites
    -0.63
    events
    -0.62
    POSITIVE LOGITS
    unci
    1.34
    izens
    1.32
    unciation
    1.26
    igration
    1.08
    izen
    1.01
    ounces
    1.01
    igr
    0.98
    igrated
    0.97
     den
    0.93
    ominated
    0.93
    Activations Density 0.007%

    No Known Activations