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. 12979
    Prev
    Next
    INDEX
    Explanations

    instances of locations or events indicated by a specific preposition followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" and its contextually relevant phrases

    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
    vantage
    -0.65
    ombat
    -0.64
    dp
    -0.60
    OWS
    -0.58
    auer
    -0.57
    elly
    -0.56
    achy
    -0.55
    ensity
    -0.55
     âĢķ
    -0.55
    canon
    -0.55
    POSITIVE LOGITS
     Zamb
    0.66
    lication
    0.62
    uana
    0.59
     Coh
    0.57
     Roh
    0.56
     shorth
    0.53
     recess
    0.53
     dusk
    0.53
     Gim
    0.53
     holidays
    0.53
    Activations Density 0.240%

    No Known Activations