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. 6006
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions that follow some specified event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "following the" in context of events or decisions

    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
     Larson
    -0.64
    vu
    -0.63
    quote
    -0.63
     perspect
    -0.60
     underrated
    -0.59
     Ethiop
    -0.59
    adj
    -0.59
     Lub
    -0.59
    Sa
    -0.57
    adjusted
    -0.56
    POSITIVE LOGITS
     announcement
    0.84
     completion
    0.79
     arrival
    0.78
    hran
    0.77
     initial
    0.75
     enactment
    0.75
     incident
    0.73
    iry
    0.72
     consultation
    0.72
     conviction
    0.72
    Activations Density 0.141%

    No Known Activations