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. 5-RES-JB
    6. 22354
    Prev
    Next
    INDEX
    Explanations

    calls to action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Now" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Berm
    -0.80
    selage
    -0.78
    dinand
    -0.72
    xtap
    -0.72
    ashtra
    -0.71
    warts
    -0.70
    emetery
    -0.69
    ksh
    -0.65
    sym
    -0.65
    iosyncr
    -0.65
    POSITIVE LOGITS
    adays
    1.60
    here
    1.33
    heres
    0.95
    ledge
    0.81
    !,
    0.76
     Playing
    0.73
     Launcher
    0.73
     antioxid
    0.69
    ow
    0.67
     Enough
    0.66
    Activations Density 0.040%

    No Known Activations