© 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. 6865
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical assessment or urging action

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, specifically the word "and."

    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
    awed
    -0.71
    owered
    -0.71
    ãĤ´
    -0.69
    ramer
    -0.68
    interstitial
    -0.65
    cedented
    -0.65
    VERTISEMENT
    -0.64
    Contents
    -0.63
    ccording
    -0.62
    locked
    -0.62
    POSITIVE LOGITS
     preferably
    1.34
     hopefully
    1.31
     ensure
    1.19
     educate
    1.17
     allow
    1.16
     pray
    1.15
     let
    1.15
     THEN
    1.15
     prepare
    1.13
     make
    1.13
    Activations Density 0.209%

    No Known Activations