Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12150
    Prev
    Next
    INDEX
    Explanations

    words related to electronic communication and technology, specifically focusing on terms related to jitter or social media handles containing 'itter'

    oai_token-act-pair · gpt-3.5-turbo

    the word "itter" in various contexts, likely indicating a focus on social media or messaging platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lez
    -0.71
    cephal
    -0.66
     Kingdoms
    -0.65
     distinguishing
    -0.62
    urat
    -0.60
     reconstruct
    -0.60
    xon
    -0.58
    rest
    -0.58
    ways
    -0.58
     fictional
    -0.54
    POSITIVE LOGITS
    itter
    1.09
    igible
    0.85
    cair
    0.83
    geist
    0.82
    ngth
    0.79
    adobe
    0.75
    iver
    0.75
    mite
    0.75
     extraord
    0.73
    alyst
    0.72
    Activations Density 0.009%

    No Known Activations