© 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. 4-RES-JB
    11. 366
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "strike" in various contexts

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

    No Comments

    Negative Logits
    regon
    -0.73
    ettel
    -0.71
    ŀ
    -0.69
    umption
    -0.69
    glomer
    -0.66
    icter
    -0.65
    ophers
    -0.65
    raints
    -0.65
    etsk
    -0.65
    opal
    -0.65
    POSITIVE LOGITS
     strike
    1.02
     strikes
    0.84
     striking
    0.84
    breakers
    0.82
     struck
    0.81
    ters
    0.80
    force
    0.80
    strike
    0.75
    ting
    0.74
     collar
    0.71
    Activations Density 0.012%

    No Known Activations