© 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. 10-RES-JB
    11. 3042
    Prev
    Next
    INDEX
    Explanations

    phrases related to unsupported or unproven claims

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substantiation or lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NCT
    -0.73
    Ô
    -0.69
     Tycoon
    -0.68
    skirts
    -0.66
    ahime
    -0.64
    lain
    -0.63
    head
    -0.60
     Clubs
    -0.60
     Tate
    -0.59
     ARC
    -0.58
    POSITIVE LOGITS
    iated
    1.65
    ive
    1.34
    iating
    1.21
    ively
    1.19
    iation
    1.15
    iable
    1.15
    ially
    1.14
    ivable
    1.10
    iate
    1.10
    iably
    1.09
    Activations Density 0.064%

    No Known Activations