© 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. 2-RES-JB
    11. 13942
    Prev
    Next
    INDEX
    Explanations

    references or prompts related to signing up for a service

    oai_token-act-pair · gpt-3.5-turbo

    references to an action of signing up or subscribing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fidel
    -0.81
    >]
    -0.69
    ãģ®éŃĶ
    -0.67
     den
    -0.67
     sting
    -0.65
    ________________________
    -0.65
     Manson
    -0.63
    ¯¯¯¯¯¯¯¯
    -0.63
    minecraft
    -0.63
     understatement
    -0.62
    POSITIVE LOGITS
    stairs
    1.29
    grades
    1.23
    graded
    1.15
    dating
    1.15
    grading
    1.10
    dates
    1.08
    rights
    0.97
    olicy
    0.94
    adesh
    0.93
    rons
    0.89
    Activations Density 0.046%

    No Known Activations