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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 9711
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate frequency, certainty, or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aic
    -0.76
    emetery
    -0.72
     guiActiveUnfocused
    -0.66
     consequential
    -0.65
    artisan
    -0.64
    opter
    -0.62
     Window
    -0.61
     Conversation
    -0.60
    channelAvailability
    -0.59
     Meaning
    -0.58
    POSITIVE LOGITS
     knew
    1.24
     enjoys
    1.23
     remembers
    1.22
     owns
    1.21
     chose
    1.21
     took
    1.20
     prefers
    1.20
     withdrew
    1.19
     forgot
    1.17
     believes
    1.15
    Activations Density 0.302%

    No Known Activations