© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 725
    Prev
    Next
    INDEX
    Explanations

    the word "intervention."

    oai_token-act-pair · gpt-4-turbo

    terms related to external involvement or interference in a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to interventions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Export
    -0.75
    WE
    -0.73
    âĢ¢âĢ¢
    -0.69
    λ
    -0.69
    carbon
    -0.69
     Fortune
    -0.68
    ille
    -0.68
    versions
    -0.67
    Earn
    -0.66
    VK
    -0.66
    POSITIVE LOGITS
     intervention
    1.10
     interven
    0.91
     interventions
    0.90
     intervene
    0.88
    ateral
    0.86
    anke
    0.84
    arie
    0.80
     intervened
    0.80
     Intervention
    0.79
    eers
    0.77
    Activations Density 0.010%

    No Known Activations