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. 0-RES-JB
    6. 6098
    Prev
    Next
    INDEX
    Explanations

    words related to unity or unification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unity and cohesion

    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
    rog
    -0.64
    ima
    -0.64
    Bre
    -0.63
     Seek
    -0.62
     Crim
    -0.62
     Trevor
    -0.62
    /-
    -0.61
     extracts
    -0.60
     fet
    -0.60
    Footnote
    -0.60
    POSITIVE LOGITS
     unified
    3.49
     unification
    2.33
     Unified
    2.13
     cohesive
    2.05
     centralized
    1.50
     coherent
    1.45
     united
    1.44
     unity
    1.40
     consolidated
    1.38
     streamlined
    1.31
    Activations Density 0.022%

    No Known Activations