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. 6-RES-JB
    6. 17957
    Prev
    Next
    INDEX
    Explanations

    mentions of ongoing or continuous situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "still" in various contexts indicating continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insula
    -0.91
    ridges
    -0.77
    stice
    -0.74
    onential
    -0.68
     SQ
    -0.68
    DragonMagazine
    -0.67
     RTX
    -0.67
    velt
    -0.66
    ongyang
    -0.66
    ãĥ³ãĤ¸
    -0.65
    POSITIVE LOGITS
    birth
    0.95
    born
    0.90
     intact
    0.85
     reeling
    0.84
     undecided
    0.84
     alive
    0.83
     afloat
    0.80
     recovering
    0.75
     Nadu
    0.75
     undergoing
    0.74
    Activations Density 0.043%

    No Known Activations