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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 23846
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "to" and followed by actions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" in various contexts and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.65
    cyclop
    -0.63
    isp
    -0.63
    hene
    -0.62
    notation
    -0.62
    FORMATION
    -0.62
    holder
    -0.61
    ellation
    -0.61
     Donation
    -0.61
    option
    -0.61
    POSITIVE LOGITS
     justify
    1.19
    pless
    1.10
     reassure
    1.08
     illustrate
    1.07
     imply
    1.07
     convince
    1.06
     provoke
    1.05
     appease
    1.05
     motivate
    1.04
     clarify
    1.04
    Activations Density 0.162%

    No Known Activations