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. 4602
    Prev
    Next
    INDEX
    Explanations

    action verbs related to physical movement

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or activities

    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
    REF
    -0.82
    SOURCE
    -0.66
     NX
    -0.61
     UE
    -0.61
     Oaks
    -0.59
    Variable
    -0.59
    BIL
    -0.58
     Pascal
    -0.57
     radiator
    -0.57
    Asset
    -0.57
    POSITIVE LOGITS
    pace
    1.35
    creen
    1.31
    paces
    1.29
    ettings
    1.27
    hift
    1.23
    hops
    1.23
    peed
    1.22
    mith
    1.20
    heet
    1.15
    omething
    1.15
    Activations Density 0.383%

    No Known Activations