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. 6419
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "small" in various contexts, possibly related to size, amount, or scale

    oai_token-act-pair · gpt-3.5-turbo

    references to small entities or groups

    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
    èĥ
    -0.70
    emy
    -0.70
    vironment
    -0.64
    atche
    -0.63
    roit
    -0.62
    çīĪ
    -0.62
     Machina
    -0.62
    alin
    -0.62
    ILLE
    -0.61
     largeDownload
    -0.61
    POSITIVE LOGITS
    pox
    1.18
     intestine
    1.09
     consolation
    0.89
     sized
    0.87
     fry
    0.86
     (<
    0.83
    hearted
    0.83
     increments
    0.82
     batches
    0.81
     stature
    0.78
    Activations Density 0.039%

    No Known Activations