© 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. 7288
    Prev
    Next
    INDEX
    Explanations

    words related to personal accounts or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to personal accounts or storytelling

    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
    OPA
    -0.69
    upid
    -0.69
    BuyableInstoreAndOnline
    -0.67
    peror
    -0.63
    PLIED
    -0.62
    BSD
    -0.61
     GSL
    -0.60
    oppable
    -0.60
    POSE
    -0.59
    owered
    -0.59
    POSITIVE LOGITS
     anecdotes
    1.13
    ewitness
    1.12
     testimonies
    1.12
     recounted
    1.06
     tales
    1.05
     testim
    1.04
     anecd
    0.99
     anecdote
    0.96
     vividly
    0.96
     recollection
    0.95
    Activations Density 0.465%

    No Known Activations