© 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. 19494
    Prev
    Next
    INDEX
    Explanations

    entities or terms related to the word "control" or "controller."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles and positions within 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
     EntityItem
    -0.71
    EMP
    -0.70
    PRES
    -0.67
     HIP
    -0.65
     homeland
    -0.63
     CLSID
    -0.63
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.62
    REM
    -0.61
    LOD
    -0.60
     Declaration
    -0.59
    POSITIVE LOGITS
    ogical
    1.42
    oola
    1.15
    anguage
    1.09
    ounge
    1.02
    ogie
    1.01
    ateral
    0.97
    ibrary
    0.96
    ife
    0.96
    iberal
    0.94
    ution
    0.93
    Activations Density 0.007%

    No Known Activations