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. 14568
    Prev
    Next
    INDEX
    Explanations

    words related to fast-paced, quick changes or growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate rapid change or growth

    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
    pel
    -0.84
     Parables
    -0.81
    tein
    -0.74
    ador
    -0.74
    quickShipAvailable
    -0.73
     commandments
    -0.73
    liga
    -0.71
    anmar
    -0.70
    hum
    -0.68
    raints
    -0.67
    POSITIVE LOGITS
     paced
    1.08
     deterior
    0.94
     accelerating
    0.87
     approaching
    0.83
     outp
    0.79
     accelerate
    0.76
     metabol
    0.76
     combust
    0.75
     ILCS
    0.74
     assimil
    0.73
    Activations Density 0.008%

    No Known Activations