© 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. 8994
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to alternatives or different options

    oai_token-act-pair · gpt-3.5-turbo

    references to alternatives or alternate concepts and solutions

    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
    artney
    -0.75
    Mar
    -0.65
     majesty
    -0.65
    agers
    -0.65
    ursed
    -0.64
    ager
    -0.63
    Import
    -0.63
    Performance
    -0.63
    girls
    -0.62
    oooo
    -0.62
    POSITIVE LOGITS
     Altern
    1.14
    altern
    1.08
    atives
    1.07
     alternative
    0.96
    Alternative
    0.92
    ative
    0.89
     Alternative
    0.87
    ATIVE
    0.83
     alternatives
    0.82
     alternate
    0.80
    Activations Density 0.008%

    No Known Activations