© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16111
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or intention

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "to" and variations of its usage

    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
     meant
    -0.57
     enough
    -0.53
     stru
    -0.53
     bruising
    -0.53
     messing
    -0.53
     coupled
    -0.52
     glitches
    -0.51
     compared
    -0.51
     vulner
    -0.51
    typ
    -0.50
    POSITIVE LOGITS
    ggles
    1.44
    wered
    1.33
    ilet
    1.18
    asted
    1.16
    ppers
    1.15
    asts
    1.10
    pless
    1.07
    pper
    1.06
     accompany
    1.04
    asting
    1.04
    Activations Density 0.172%

    No Known Activations