© 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. 8-RES-JB
    11. 3094
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation and reason

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating emotional or impactful sentiments

    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
     sought
    -0.70
    atel
    -0.65
     manually
    -0.64
     coveted
    -0.64
     battled
    -0.63
     declared
    -0.62
     retained
    -0.61
     surrounds
    -0.61
     slashed
    -0.59
     cel
    -0.58
    POSITIVE LOGITS
     sense
    0.87
     me
    0.82
     tremend
    0.82
    hift
    0.79
     alot
    0.78
    quickShipAvailable
    0.77
    OME
    0.74
    soType
    0.72
    emi
    0.70
    ENSE
    0.70
    Activations Density 0.191%

    No Known Activations