© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19803
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "ster"

    oai_token-act-pair · gpt-3.5-turbo

    words ending with the suffix "ster"

    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
    ittance
    -0.74
    ĸļ
    -0.71
    Reviewer
    -0.68
     hem
    -0.68
    ĪĴ
    -0.68
    iferation
    -0.67
    olulu
    -0.67
     skeptical
    -0.67
    endment
    -0.67
    Ĥ¬
    -0.65
    POSITIVE LOGITS
    fish
    0.93
    bucks
    0.90
    oids
    0.90
     Awakens
    0.86
    geist
    0.85
    wolves
    0.83
    ranean
    0.81
    door
    0.81
    odon
    0.81
    ster
    0.80
    Activations Density 0.014%

    No Known Activations