© 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. 6236
    Prev
    Next
    INDEX
    Explanations

    phrases related to a persistent and consistent effort or action

    oai_token-act-pair · gpt-3.5-turbo

    the word "paint" and its variations, particularly in contexts related to tasks or projects

    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
     silenced
    -0.75
     reciproc
    -0.71
    BUS
    -0.68
     calcul
    -0.67
     hybrids
    -0.65
     economists
    -0.60
     lob
    -0.60
     slots
    -0.60
     logical
    -0.60
     synd
    -0.60
    POSITIVE LOGITS
    aint
    4.66
    aints
    3.33
    ainted
    2.16
    aintain
    1.71
    ain
    1.48
    aine
    1.18
    ained
    1.15
    ains
    1.11
    aining
    1.05
    astered
    1.02
    Activations Density 0.018%

    No Known Activations