© 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. 10-RES-JB
    11. 12676
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thanks directed towards specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.80
    Gi
    -0.79
    heid
    -0.75
    soDeliveryDate
    -0.68
    HS
    -0.67
    ieties
    -0.66
    isa
    -0.65
    ausible
    -0.64
    aults
    -0.63
    ire
    -0.63
    POSITIVE LOGITS
     helping
    1.30
     rescuing
    1.22
     bringing
    1.21
     saving
    1.20
     letting
    1.19
     recognizing
    1.19
     allowing
    1.17
     reminding
    1.13
     providing
    1.13
     preserving
    1.13
    Activations Density 0.094%

    No Known Activations