© 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. 17887
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of first-person pronouns and collective expressions

    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
     outwe
    -0.77
     Carlton
    -0.75
     prize
    -0.71
     slam
    -0.71
     puberty
    -0.70
     ambassadors
    -0.69
     plush
    -0.66
     inexper
    -0.66
     nationals
    -0.66
     spoil
    -0.65
    POSITIVE LOGITS
    Output
    1.17
    Notice
    1.07
    Example
    1.04
    Usage
    1.02
    Same
    1.02
    RAW
    1.01
    Simple
    1.00
    example
    1.00
    Note
    0.99
    Alternatively
    0.97
    Activations Density 0.116%

    No Known Activations