© 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. 12909
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical equipment and settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the past tense verb "did."

    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
     Scholar
    -0.66
    zai
    -0.65
     Drum
    -0.64
     Portable
    -0.61
     Pul
    -0.61
     Lambert
    -0.61
     Salon
    -0.60
     Fug
    -0.60
     Frag
    -0.59
     Spur
    -0.59
    POSITIVE LOGITS
    ividual
    1.31
    rew
    1.07
    oubted
    1.05
    iscover
    1.03
    onna
    1.02
    etermined
    1.01
    oubt
    0.98
    yssey
    0.97
    ynamic
    0.96
    rown
    0.96
    Activations Density 0.023%

    No Known Activations