© 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. 8-RES-JB
    6. 20059
    Prev
    Next
    INDEX
    Explanations

    phrases related to examining roles or situations in a critical or analytical manner

    oai_token-act-pair · gpt-3.5-turbo

    references to roles and responsibilities within scientific and creative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mos
    -0.68
    Dialog
    -0.62
     Junk
    -0.62
    Alert
    -0.62
     Cancel
    -0.60
     Written
    -0.60
    Roll
    -0.60
     Protest
    -0.60
    Vote
    -0.59
     UNCLASSIFIED
    -0.59
    POSITIVE LOGITS
     often
    0.85
    often
    0.80
     seldom
    0.79
     rarely
    0.77
    entimes
    0.77
     inherent
    0.75
    chnology
    0.74
     specialized
    0.73
    versely
    0.72
     typically
    0.71
    Activations Density 0.617%

    No Known Activations