© 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. 9-RES-JB
    11. 15821
    Prev
    Next
    INDEX
    Explanations

    words related to estimating or establishing something

    oai_token-act-pair · gpt-3.5-turbo

    the word "Est" and its variations, indicating a focus on establishing facts or estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stocks
    -0.84
    tty
    -0.75
    pton
    -0.72
    pload
    -0.71
    orld
    -0.68
    Õ
    -0.65
    birds
    -0.64
    strap
    -0.64
    ãģĭ
    -0.63
    beit
    -0.63
    POSITIVE LOGITS
    ablished
    1.46
    ablish
    1.43
    imate
    1.43
    imated
    1.36
    imates
    1.35
    imating
    1.34
    hetics
    1.25
    uary
    1.22
    imation
    1.18
    ablishment
    1.15
    Activations Density 0.041%

    No Known Activations