© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 1671
    Prev
    Next
    INDEX
    Explanations

    the word "dip" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dip" and its variations in various contexts

    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
     WATCHED
    -0.77
    Reply
    -0.75
    ÙIJ
    -0.71
     Crusade
    -0.71
     ACTIONS
    -0.68
     Asylum
    -0.68
    Made
    -0.67
    fare
    -0.66
     SPORTS
    -0.66
    scape
    -0.63
    POSITIVE LOGITS
    shit
    1.12
    artisan
    1.08
     dipping
    1.03
    pty
    0.97
    otom
    0.93
    iphany
    0.90
    ients
    0.90
    irts
    0.88
    ole
    0.88
    aminer
    0.88
    Activations Density 0.019%

    No Known Activations