© 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. 21592
    Prev
    Next
    INDEX
    Explanations

    the word "ult" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    the suffix 'ult' 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
     Blaz
    -0.69
    CHR
    -0.68
    BY
    -0.67
    bes
    -0.62
    strings
    -0.62
    forth
    -0.61
    STON
    -0.61
    女
    -0.61
    ¶ħ
    -0.60
    hold
    -0.60
    POSITIVE LOGITS
    raviolet
    1.15
    imately
    1.13
    iple
    1.12
    icultural
    1.03
    imates
    1.01
    iful
    0.94
    ult
    0.94
    icide
    0.93
    urally
    0.91
    icult
    0.91
    Activations Density 0.007%

    No Known Activations