© 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. 9967
    Prev
    Next
    INDEX
    Explanations

    instances of dates or years

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "be" in various contexts

    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
     sqor
    -0.71
    icago
    -0.66
     nap
    -0.65
     fray
    -0.64
     partName
    -0.62
     confinement
    -0.61
     Saying
    -0.61
     chatter
    -0.60
     relativity
    -0.60
    vas
    -0.59
    POSITIVE LOGITS
     replaced
    1.05
     released
    1.04
     implemented
    0.99
    amed
    0.96
     distributed
    0.95
     unveiled
    0.94
     executed
    0.93
     overseen
    0.92
     delivered
    0.92
     administered
    0.92
    Activations Density 0.072%

    No Known Activations