© 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. 22360
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of retrying or attempting again

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ry" and related terms that suggest hunger or scarcity

    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
     equity
    -0.65
     uphill
    -0.62
     Ultimate
    -0.60
     institutional
    -0.59
     downhill
    -0.58
     attribut
    -0.58
     vested
    -0.57
     atro
    -0.57
     Twin
    -0.56
     withholding
    -0.56
    POSITIVE LOGITS
    ry
    4.65
    ries
    2.53
    RY
    2.42
    rys
    2.20
    rying
    2.13
    ried
    1.73
    rie
    1.53
    ryn
    1.47
    rey
    1.39
    rily
    1.37
    Activations Density 0.015%

    No Known Activations