© 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. 7-RES-JB
    11. 9722
    Prev
    Next
    INDEX
    Explanations

    names in Twitter handles or usernames

    oai_token-act-pair · gpt-3.5-turbo

    usernames or handles associated with social media accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captcha
    -0.74
     seals
    -0.68
     jaws
    -0.66
     technicians
    -0.66
     fluid
    -0.65
     vacuum
    -0.65
     cart
    -0.63
     breadth
    -0.62
     solvent
    -0.61
     shrink
    -0.61
    POSITIVE LOGITS
    Jr
    1.21
    _(
    0.92
    /)
    0.86
    CTV
    0.86
    @
    0.85
    _
    0.83
    Media
    0.83
    _-_
    0.83
    __
    0.79
    />
    0.77
    Activations Density 0.071%

    No Known Activations