© 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. 6-RES-JB
    11. 300
    Prev
    Next
    INDEX
    Explanations

    questions related to decision-making or comparison

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements about identity and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APTER
    -0.66
    VERTISEMENT
    -0.65
    ISON
    -0.64
    lass
    -0.58
    sworth
    -0.58
     Dragonbound
    -0.57
     ===
    -0.56
     SAL
    -0.54
    tips
    -0.54
     ARM
    -0.54
    POSITIVE LOGITS
    abouts
    1.17
    depending
    0.90
     alternatively
    0.89
    gans
    0.83
    phans
    0.81
    Else
    0.78
     unlucky
    0.75
    acle
    0.74
     depending
    0.74
    inx
    0.73
    Activations Density 0.149%

    No Known Activations