© 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. 10-RES-JB
    11. 7443
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements regarding potential outcomes or consequences

    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
    noticed
    -0.77
     Lawrence
    -0.75
     Named
    -0.69
     Klu
    -0.68
     Died
    -0.64
     Loyal
    -0.63
    stood
    -0.62
     headquartered
    -0.62
    Favorite
    -0.60
     watches
    -0.60
    POSITIVE LOGITS
     suffice
    1.25
     entail
    1.17
     alleviate
    1.09
     elicit
    1.09
     complicate
    1.07
     preclude
    1.04
     result
    1.03
     necess
    1.03
     mean
    1.01
     require
    0.99
    Activations Density 0.194%

    No Known Activations