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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 8747
    Prev
    Next
    INDEX
    Explanations

    terms related to Google and different locations or activities near the sea, often involving activities or features of the sea

    oai_token-act-pair · gpt-3.5-turbo

    instances of terms related to web searching and online presence

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

    No Comments

    Negative Logits
    soDeliveryDate
    -0.71
    )=(
    -0.64
     ISI
    -0.64
     necessity
    -0.62
     HERO
    -0.62
     abbre
    -0.61
     delays
    -0.56
    channelAvailability
    -0.55
     constraints
    -0.55
     CPS
    -0.54
    POSITIVE LOGITS
    vine
    0.69
    kiss
    0.69
    ogun
    0.67
    mans
    0.67
     Pony
    0.67
    wine
    0.67
    olit
    0.66
    oche
    0.66
    kees
    0.65
     Owl
    0.65
    Activations Density 0.220%

    No Known Activations