© 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. 7-RES-JB
    11. 8649
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical activities or instructions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to actions and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©Ł
    -0.74
     Historic
    -0.56
    Merit
    -0.55
    ãĤ«
    -0.54
    ãĥĥãĥĪ
    -0.54
     Canaver
    -0.53
     respectively
    -0.51
     Establishment
    -0.51
    helial
    -0.50
    pmwiki
    -0.49
    POSITIVE LOGITS
     someday
    0.77
     or
    0.63
     yourself
    0.60
     oneself
    0.59
    omever
    0.59
     tomorrow
    0.58
    ecause
    0.58
     seiz
    0.57
    idav
    0.57
     ;)
    0.56
    Activations Density 1.551%

    No Known Activations