© 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. 22872
    Prev
    Next
    INDEX
    Explanations

    phrases containing political or authoritative statements that are emphasized with special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols indicating emphasis or special notation

    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
    eers
    -0.67
     playbook
    -0.66
     sew
    -0.65
     nod
    -0.64
     diversion
    -0.64
     chall
    -0.64
    senal
    -0.63
     guiActiveUnfocused
    -0.63
    iewicz
    -0.63
     lair
    -0.63
    POSITIVE LOGITS
    there
    0.94
    certain
    0.91
    ihad
    0.87
    nob
    0.86
    someone
    0.85
    while
    0.84
    fter
    0.83
    these
    0.82
    they
    0.82
    return
    0.80
    Activations Density 0.138%

    No Known Activations