© 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. 7-RES-JB
    11. 2674
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical presence or visiting

    oai_token-act-pair · gpt-3.5-turbo

    mentions of presence and physical attendance at events or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orically
    -0.74
    attribute
    -0.71
     Attribution
    -0.71
     derivatives
    -0.68
     spir
    -0.68
     regression
    -0.67
    Percent
    -0.66
    Ĭ±
    -0.66
     hybrids
    -0.65
     consolidation
    -0.64
    POSITIVE LOGITS
     anytime
    0.81
     greets
    0.80
     meals
    0.79
     greet
    0.75
     voluntarily
    0.74
     dinner
    0.74
     booth
    0.73
     Guests
    0.73
    site
    0.72
     meetings
    0.72
    Activations Density 0.402%

    No Known Activations