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. 1-RES-JB
    6. 23743
    Prev
    Next
    INDEX
    Explanations

    phrases related to coherence and cohesion

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to coherence and cohesion in narratives or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VR
    -0.68
    vr
    -0.66
    ALT
    -0.65
    OUT
    -0.65
    AUT
    -0.63
    von
    -0.63
    AF
    -0.62
    psy
    -0.62
    NS
    -0.61
    gun
    -0.61
    POSITIVE LOGITS
     coherent
    1.36
     cohesion
    1.11
    ively
    1.07
    herence
    1.04
    herent
    1.01
     cohesive
    0.95
     explan
    0.93
     inco
    0.91
    ly
    0.85
     charact
    0.84
    Activations Density 0.011%

    No Known Activations