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. 0-RES-JB
    6. 17887
    Prev
    Next
    INDEX
    Explanations

    words related to direction and physical body parts, specifically 'upstream' and 'trunk'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to upstream and downstream processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Las
    -0.77
    ookie
    -0.75
     Las
    -0.73
     dressing
    -0.70
     Mickey
    -0.68
     Crusade
    -0.67
     fle
    -0.66
     cand
    -0.66
     Wiz
    -0.66
    lis
    -0.65
    POSITIVE LOGITS
     upstream
    4.17
     downstream
    3.93
     inland
    1.27
    river
    1.25
     ashore
    1.23
    stream
    1.16
     dams
    1.07
     GCC
    1.04
     waterfall
    1.00
     raft
    1.00
    Activations Density 0.039%

    No Known Activations