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. 1685
    Prev
    Next
    INDEX
    Explanations

    names containing the token 'tt'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "tt" in various contexts

    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
    actionDate
    -0.77
    EStream
    -0.67
     propensity
    -0.66
    Reviewer
    -0.65
    SOURCE
    -0.64
    Ĥİ
    -0.64
    ħĭ
    -0.63
     distilled
    -0.62
     POLITICO
    -0.62
     circulation
    -0.61
    POSITIVE LOGITS
    ilts
    1.07
    tt
    1.06
    achment
    1.02
    ilt
    0.98
    uning
    0.97
    ail
    0.94
    leneck
    0.93
    uesday
    0.93
    olkien
    0.93
    rox
    0.93
    Activations Density 0.006%

    No Known Activations