© 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. 23622
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "CR" followed by a number as an identifier

    oai_token-act-pair · gpt-3.5-turbo

    references to "CR" followed by various numerical codes

    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
    lihood
    -0.94
    chest
    -0.85
    liness
    -0.82
     Ukrainian
    -0.75
    lies
    -0.75
     Filipino
    -0.72
    smanship
    -0.71
    lav
    -0.71
     Nigerian
    -0.70
     Lumpur
    -0.69
    POSITIVE LOGITS
    EDIT
    1.02
    ACK
    0.96
    ISIS
    0.96
    ASH
    0.92
    udence
    0.92
    OSS
    0.90
    ursor
    0.87
    isco
    0.85
    AMP
    0.83
    PF
    0.81
    Activations Density 0.014%

    No Known Activations