© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13510
    Prev
    Next
    INDEX
    Explanations

    terms related to keyboards and input devices

    oai_token-act-pair · gpt-3.5-turbo

    references to keyboards and associated input devices

    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
    asca
    -0.76
     Expend
    -0.73
     Leone
    -0.73
     Gund
    -0.72
     Volunte
    -0.68
    lli
    -0.67
     Bett
    -0.67
    zona
    -0.66
     Scient
    -0.65
    IONS
    -0.65
    POSITIVE LOGITS
     shortcuts
    1.13
    caps
    1.06
     shortcut
    0.99
     keyboard
    0.97
     layouts
    0.94
     keyboards
    0.91
     layout
    0.91
     keys
    0.89
    cap
    0.86
    */(
    0.85
    Activations Density 0.033%

    No Known Activations