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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14580
    Prev
    Next
    INDEX
    Explanations

    words related to auditory cues, like sounds such as bells and whistles, and words related to the action of piping or installing something

    oai_token-act-pair · gpt-3.5-turbo

    references to sounds and actions involving whistling and piping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اÙĦ
    -0.68
    pora
    -0.68
    ignment
    -0.67
    igslist
    -0.63
    Reloaded
    -0.61
    photos
    -0.61
     indictment
    -0.61
     Defeat
    -0.61
     Madness
    -0.61
     Agency
    -0.59
    POSITIVE LOGITS
     whist
    1.19
    elines
    0.99
    ledged
    0.97
    rote
    0.90
    vernment
    0.84
     pip
    0.84
     snipp
    0.82
    itone
    0.78
    eworks
    0.77
    icket
    0.77
    Activations Density 0.010%

    No Known Activations