© 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. 9-RES-JB
    11. 5261
    Prev
    Next
    INDEX
    Explanations

    mentions of formal events or introductions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a welcome or introduction to an event or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.75
    okia
    -0.68
    hes
    -0.67
    ahon
    -0.67
    gross
    -0.66
    lied
    -0.66
    etooth
    -0.65
     externalToEVAOnly
    -0.65
     cumbers
    -0.65
    leneck
    -0.65
    POSITIVE LOGITS
     Subtle
    0.97
     FREE
    0.83
     Welcome
    0.82
     Minute
    0.82
     NEW
    0.79
     Planet
    0.78
     Encyclopedia
    0.75
     STATS
    0.75
     CLASS
    0.73
     another
    0.72
    Activations Density 0.114%

    No Known Activations