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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 14317
    Prev
    Next
    INDEX
    Explanations

    phrases related to setups or instructions

    oai_token-act-pair · gpt-3.5-turbo

    the word "for" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.89
    leased
    -0.74
    jad
    -0.72
    iewicz
    -0.70
    beat
    -0.68
    itle
    -0.67
    quartered
    -0.65
    Occup
    -0.65
    heny
    -0.65
    essions
    -0.65
    POSITIVE LOGITS
     simplicity
    1.25
     clarity
    1.21
     convenience
    1.17
     sake
    1.16
     purposes
    1.11
     ease
    1.09
     optimal
    1.09
     optimum
    1.07
     easier
    1.05
     each
    1.04
    Activations Density 0.149%

    No Known Activations