© 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. 12654
    Prev
    Next
    INDEX
    Explanations

    names or terms containing "Spe" followed by a number, potentially referring to a specific individual or specialized subject matter

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "speak" or variations of it

    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
    etheless
    -0.88
    enegger
    -0.76
    hap
    -0.72
     guiActiveUnfocused
    -0.69
     Leilan
    -0.69
    imaru
    -0.67
    maxwell
    -0.66
    orage
    -0.65
    ogens
    -0.65
    1945
    -0.65
    POSITIVE LOGITS
     Spe
    1.05
    spe
    1.03
    Spe
    0.96
    eches
    0.93
    akers
    0.88
    lling
    0.88
    culation
    0.87
    eding
    0.84
    acher
    0.81
    eters
    0.81
    Activations Density 0.009%

    No Known Activations