© 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. 4-RES-JB
    11. 16295
    Prev
    Next
    INDEX
    Explanations

    Amazon Echo and related products

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Echo" device and its functionalities

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

    No Comments

    Negative Logits
    hirt
    -0.83
    oppable
    -0.82
    amins
    -0.80
    alcohol
    -0.79
    EH
    -0.78
    EW
    -0.77
    acca
    -0.76
    andals
    -0.71
    iyah
    -0.70
    ijk
    -0.70
    POSITIVE LOGITS
     chamber
    0.85
     Chamber
    0.79
    ãĥ¼ãĥĨãĤ£
    0.77
     chambers
    0.77
    piece
    0.75
     Echo
    0.70
     Cyn
    0.69
    arthed
    0.69
     Valley
    0.67
    hower
    0.67
    Activations Density 0.013%

    No Known Activations