© 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. 9-RES-JB
    11. 18526
    Prev
    Next
    INDEX
    Explanations

    phrases related to adapting to changing circumstances

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to adaptation and changing circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Smile
    -0.69
    saf
    -0.68
    bys
    -0.65
    Shares
    -0.64
     aborted
    -0.64
    hemat
    -0.61
    uve
    -0.60
    rity
    -0.60
    FIR
    -0.60
    mination
    -0.59
    POSITIVE LOGITS
     realities
    1.21
     adversity
    1.15
     pressures
    1.11
     situations
    1.03
     demands
    1.02
     predic
    0.99
     onslaught
    0.99
     evolving
    0.99
     complexities
    0.98
    ctic
    0.98
    Activations Density 0.646%

    No Known Activations