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. 4-RES-JB
    6. 21443
    Prev
    Next
    INDEX
    Explanations

    phrases related to conversations and discussions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    dialogue or conversational elements

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

    No Comments

    Negative Logits
    surprisingly
    -0.61
     :=
    -0.60
    uitive
    -0.59
    minist
    -0.57
    ieu
    -0.57
     âĢº
    -0.54
     Austral
    -0.53
    ministic
    -0.53
    arist
    -0.51
    stellar
    -0.51
    POSITIVE LOGITS
    )."
    1.47
    .")
    1.41
    .'"
    1.36
    '."
    1.26
    ]."
    1.24
    !'"
    1.23
    ").
    1.23
    )"
    1.18
     â̦"
    1.15
    '"
    1.06
    Activations Density 1.826%

    No Known Activations