Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3476
    Prev
    Next
    INDEX
    Explanations

    conversational phrases with an informal tone

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and sentiments

    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
    etheless
    -0.81
    uitive
    -0.77
    cture
    -0.76
    prisingly
    -0.73
    surprisingly
    -0.69
     :=
    -0.67
    ----------------------------------------------------------------
    -0.66
    minist
    -0.66
    inction
    -0.65
     largeDownload
    -0.60
    POSITIVE LOGITS
    .")
    1.44
    '."
    1.28
    ").
    1.24
    .'"
    1.23
    '"
    1.21
    !'"
    1.20
    ',"
    1.10
    "]
    1.08
    ,'"
    1.07
    ")
    1.05
    Activations Density 0.322%

    No Known Activations