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. 2-RES-JB
    6. 20482
    Prev
    Next
    INDEX
    Explanations

    phrases or statements that are being repeated or emphasized

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iop
    -0.81
    Torrent
    -0.73
    ipel
    -0.73
    RH
    -0.73
    mile
    -0.70
    onz
    -0.69
    opic
    -0.69
    oping
    -0.68
    Offline
    -0.68
    lio
    -0.65
    POSITIVE LOGITS
     reiter
    1.08
     reaff
    1.01
     reiterated
    0.88
     affirmation
    0.86
     vows
    0.84
     reiterate
    0.83
     affirm
    0.78
     disav
    0.71
     underscores
    0.70
     repud
    0.69
    Activations Density 0.015%

    No Known Activations