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. 7-RES-JB
    6. 13000
    Prev
    Next
    INDEX
    Explanations

    Twitter handles starting with "On"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "On" and its variations indicating a timing or scheduling context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILY
    -0.64
    OULD
    -0.64
     Inquisition
    -0.61
     DOI
    -0.60
     Keys
    -0.60
    MODE
    -0.60
    oother
    -0.56
    illac
    -0.55
    enance
    -0.55
     artific
    -0.55
    POSITIVE LOGITS
    coming
    1.45
    slaught
    1.30
     behalf
    1.14
    demand
    1.10
    eday
    1.09
    shore
    1.09
    yx
    1.04
    sight
    1.03
    etime
    1.03
    slow
    1.00
    Activations Density 0.098%

    No Known Activations