© 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. 7325
    Prev
    Next
    INDEX
    Explanations

    technical information related to data input and retrieval

    oai_token-act-pair · gpt-3.5-turbo

    structured data such as dates, times, and formatting requirements in information

    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
    Improve
    -0.84
    Decre
    -0.66
    olen
    -0.65
    issance
    -0.65
    Improved
    -0.64
    Impro
    -0.64
    umerable
    -0.63
     disg
    -0.63
    raq
    -0.61
    ateurs
    -0.60
    POSITIVE LOGITS
     location
    1.55
     name
    1.54
     date
    1.41
     coordinates
    1.28
     username
    1.27
     dates
    1.27
     names
    1.27
     initials
    1.26
    name
    1.25
     surname
    1.22
    Activations Density 1.032%

    No Known Activations