© 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. 0-RES-JB
    11. 6374
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    past participles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.61
    FORE
    -0.58
    OWER
    -0.56
    GET
    -0.54
    OPLE
    -0.53
    otine
    -0.52
    #$#$
    -0.52
    uggage
    -0.51
    wives
    -0.50
     Harbour
    -0.50
    POSITIVE LOGITS
    ed
    3.97
    edly
    2.52
    eds
    2.15
    ED
    2.02
    ing
    1.78
    edin
    1.70
    ered
    1.59
    edIn
    1.55
    ned
    1.49
    edes
    1.49
    Activations Density 0.046%

    No Known Activations