© 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. 2-RES-JB
    11. 13019
    Prev
    Next
    INDEX
    Explanations

    words related to ejection or expulsion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ejection or removal

    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
    ãĤ·ãĥ£
    -0.85
    aido
    -0.82
    krit
    -0.75
    externalActionCode
    -0.74
    intel
    -0.72
    gem
    -0.70
    Else
    -0.69
     McKin
    -0.67
    Pros
    -0.67
    Correct
    -0.67
    POSITIVE LOGITS
     eject
    1.16
     ejected
    0.85
     pods
    0.78
    lehem
    0.73
     dun
    0.70
    eatures
    0.70
    owship
    0.69
    rieved
    0.68
     Boe
    0.67
     attendants
    0.67
    Activations Density 0.014%

    No Known Activations