© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    keywords related to the concept of opening or initializing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to open-source software

    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
     Brach
    -0.74
     Bane
    -0.72
    iage
    -0.71
     Witches
    -0.68
     Cabrera
    -0.66
     artific
    -0.65
    ersive
    -0.65
    Bey
    -0.64
     Tate
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
    POSITIVE LOGITS
    SSL
    1.00
    office
    0.93
    Frameworks
    0.86
    GL
    0.85
    stack
    0.84
    NAS
    0.76
    open
    0.75
    Office
    0.74
    Street
    0.73
    ahead
    0.72
    Activations Density 0.023%

    No Known Activations