Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3520
    Prev
    Next
    INDEX
    Explanations

    instances of receiving communication or gifts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of receiving messages or notifications

    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
    onge
    -0.74
    istan
    -0.67
    occupied
    -0.66
    istence
    -0.64
    fights
    -0.63
    players
    -0.63
     gaps
    -0.62
     loopholes
    -0.61
    iny
    -0.61
     corners
    -0.61
    POSITIVE LOGITS
     invitation
    1.10
     congrat
    1.00
     notification
    1.00
     congratulations
    0.95
     accol
    0.93
     gift
    0.93
     reprim
    0.93
     invitations
    0.91
     endorsement
    0.91
     permission
    0.89
    Activations Density 0.233%

    No Known Activations