© 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. 3677
    Prev
    Next
    INDEX
    Explanations

    the verb "is" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that provide clarity on the interpretation or explanation of events

    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
    bies
    -0.76
    usercontent
    -0.72
     horizont
    -0.66
     actionGroup
    -0.64
    ividual
    -0.63
     IDs
    -0.62
    astically
    -0.61
    ifferent
    -0.61
     dumps
    -0.61
    ividually
    -0.60
    POSITIVE LOGITS
    ĺħ
    1.02
     why
    0.85
    SPONSORED
    0.67
     suspic
    0.65
     reassuring
    0.65
     Rasmussen
    0.64
     what
    0.64
    PORT
    0.64
     understatement
    0.63
     Canaver
    0.63
    Activations Density 0.158%

    No Known Activations