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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 14198
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 60

    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
     Flavoring
    -0.84
    ches
    -0.77
    achi
    -0.72
    cedes
    -0.71
    lies
    -0.70
    leased
    -0.70
    rious
    -0.70
    abolic
    -0.68
    plement
    -0.67
    ilater
    -0.67
    POSITIVE LOGITS
     Minutes
    1.33
    Hz
    0.94
    fps
    0.93
     ILCS
    0.89
     Hz
    0.86
     Seconds
    0.81
     mph
    0.78
     seconds
    0.76
    mph
    0.76
     fps
    0.75
    Activations Density 0.034%

    No Known Activations