© 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. 7-RES-JB
    11. 8709
    Prev
    Next
    INDEX
    Explanations

    terminology related to powerful influences or impactful entities

    oai_token-act-pair · gpt-3.5-turbo

    references to various forces that influence behavior and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecause
    -0.83
    oat
    -0.79
    oses
    -0.79
    DERR
    -0.79
    guyen
    -0.77
    reciation
    -0.76
    algia
    -0.73
    heid
    -0.73
    mbuds
    -0.73
    sterdam
    -0.73
    POSITIVE LOGITS
     exerted
    1.09
     force
    0.98
     maj
    0.96
     multiplier
    0.96
     shaping
    0.86
     underpin
    0.81
     influencing
    0.81
     Awakens
    0.80
     powering
    0.78
     imbalance
    0.78
    Activations Density 0.045%

    No Known Activations