© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    phrases related to influence or power

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in" in various contexts

    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
    PIN
    -0.73
    OTUS
    -0.67
    Enlarge
    -0.66
    chuk
    -0.65
    Sold
    -0.59
    """
    -0.59
    Mand
    -0.57
    toggle
    -0.56
     spectrum
    -0.55
    inea
    -0.55
    POSITIVE LOGITS
    anwhile
    0.80
    enegger
    0.76
     notwithstanding
    0.68
    enture
    0.67
     preferably
    0.66
    etheless
    0.65
    fortunately
    0.65
     unsurprisingly
    0.63
     largeDownload
    0.62
    shows
    0.62
    Activations Density 1.398%

    No Known Activations