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. 6-RES-JB
    6. 13023
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to the place 'Sumatra'

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Sum" and its relevance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.66
     livest
    -0.63
     grounding
    -0.62
    cffff
    -0.60
     fatty
    -0.58
    RAFT
    -0.58
     sleeve
    -0.57
     blinking
    -0.57
    OHN
    -0.56
     pig
    -0.56
    POSITIVE LOGITS
    mers
    1.20
    ming
    1.17
    mits
    1.04
    mons
    1.04
    atra
    1.03
    sum
    0.94
    mar
    0.92
    plings
    0.88
    ption
    0.88
    otaur
    0.86
    Activations Density 0.017%

    No Known Activations