Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 18730
    Prev
    Next
    INDEX
    Explanations

    verbs in possessive form

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the letter 's'

    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
    EStream
    -0.71
    uliffe
    -0.68
     adjunct
    -0.65
    EStreamFrame
    -0.63
     Leilan
    -0.63
     controls
    -0.63
     displ
    -0.60
     boycot
    -0.60
    illac
    -0.60
     calculating
    -0.59
    POSITIVE LOGITS
    lightly
    1.04
    atisf
    1.00
    omew
    0.96
    ources
    0.96
    aved
    0.93
    wered
    0.93
    ouls
    0.92
    ond
    0.91
    uddenly
    0.91
    ustain
    0.90
    Activations Density 0.256%

    No Known Activations