© 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. 17619
    Prev
    Next
    INDEX
    Explanations

    references to the term "Cygnus"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Cy", possibly indicating a focus on related entities or subjects within a specific context

    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
     guiActiveUnfocused
    -1.01
    ãģį
    -0.83
    IFIED
    -0.76
    etts
    -0.76
     relativity
    -0.72
    DERR
    -0.71
    ifice
    -0.71
    UGE
    -0.70
    furt
    -0.70
    raints
    -0.69
    POSITIVE LOGITS
    cles
    1.36
    prus
    1.27
    clone
    1.03
    ©¶æ
    1.01
    cling
    1.00
    cle
    0.99
    ynes
    0.93
     Cy
    0.86
    nian
    0.86
    bil
    0.85
    Activations Density 0.013%

    No Known Activations