© 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. 6418
    Prev
    Next
    INDEX
    Explanations

    phrases indicating some form of authentication or verification

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to identity verification or CAPTCHA processes

    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
    }}}
    -0.76
    '>
    -0.61
    pmwiki
    -0.60
    aughs
    -0.60
    etts
    -0.59
     Names
    -0.59
    benefit
    -0.58
    antine
    -0.58
     Classification
    -0.57
    FactoryReloaded
    -0.56
    POSITIVE LOGITS
    user
    0.66
     subscribed
    0.61
    registered
    0.58
     subscrib
    0.57
    pad
    0.57
    interstitial
    0.56
     spam
    0.55
    inged
    0.55
    cgi
    0.54
     robot
    0.54
    Activations Density 0.015%

    No Known Activations