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. 3955
    Prev
    Next
    INDEX
    Explanations

    phrases related to productivity or output

    oai_token-act-pair · gpt-3.5-turbo

    terms related to yielding or producing outcomes, particularly in financial or resource 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
    hemat
    -0.66
     tox
    -0.64
    zai
    -0.63
     compuls
    -0.62
    ype
    -0.61
    aldo
    -0.59
    hemy
    -0.59
     scapego
    -0.58
    alg
    -0.58
    ocal
    -0.58
    POSITIVE LOGITS
     yield
    1.03
     yields
    0.92
     yielding
    0.83
    ENCY
    0.83
    bang
    0.76
     yielded
    0.71
    plings
    0.69
    uces
    0.68
    onse
    0.68
    ensical
    0.68
    Activations Density 0.021%

    No Known Activations