© 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. 9-RES-JB
    11. 3267
    Prev
    Next
    INDEX
    Explanations

    phrases containing the pronoun "they" and related verbs

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific formatting or tokens that indicate the end of sections or the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Additional
    -0.55
     Additional
    -0.54
     prospect
    -0.54
    Category
    -0.54
     Windsor
    -0.52
     Central
    -0.50
     GCC
    -0.50
     contributor
    -0.50
     Strategic
    -0.49
     newcom
    -0.49
    POSITIVE LOGITS
     ain
    0.93
    zbollah
    0.82
     lied
    0.76
     wanna
    0.74
     gotta
    0.74
     fools
    0.73
    tics
    0.73
     obey
    0.72
    ngth
    0.71
     hates
    0.71
    Activations Density 0.629%

    No Known Activations