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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 19593
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating a need for action or change

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to change or action in a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overlap
    -0.60
     PHI
    -0.60
     fluct
    -0.59
    interstitial
    -0.59
     Odd
    -0.58
     guesses
    -0.58
    glers
    -0.57
    reements
    -0.57
     graz
    -0.56
     varying
    -0.56
    POSITIVE LOGITS
     ASAP
    1.88
     urgently
    1.41
     immediately
    1.22
     sooner
    1.19
     lest
    1.18
     NOW
    1.12
     Immediately
    1.09
     BEFORE
    1.01
     promptly
    0.99
     accordingly
    0.97
    Activations Density 0.493%

    No Known Activations