© 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. 6-RES-JB
    11. 18452
    Prev
    Next
    INDEX
    Explanations

    phrases related to being inspired or motivated by specific events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating inspiration or motivation derived from various sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rek
    -0.90
    asive
    -0.81
    ilet
    -0.80
    ertain
    -0.79
    ategories
    -0.79
     transitioned
    -0.78
    inis
    -0.77
    nea
    -0.76
    ires
    -0.76
    secure
    -0.75
    POSITIVE LOGITS
     combining
    0.80
     nature
    0.77
     sheer
    0.75
     mobs
    0.73
     curiosity
    0.70
     Almighty
    0.69
     virtue
    0.69
     rumours
    0.68
     rum
    0.68
     targeting
    0.66
    Activations Density 0.070%

    No Known Activations