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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 16045
    Prev
    Next
    INDEX
    Explanations

    statements about the current state or progress of various situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the state of affairs or current conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [+]
    -0.71
     (>
    -0.66
    emark
    -0.65
     Tens
    -0.65
    pora
    -0.64
    odied
    -0.63
    affe
    -0.63
    ewitness
    -0.63
    raint
    -0.63
    ¿½
    -0.62
    POSITIVE LOGITS
     alright
    0.91
    icably
    0.89
     downhill
    0.87
     differently
    0.85
     fine
    0.84
     hun
    0.82
     ok
    0.81
     OK
    0.78
     sorted
    0.77
     okay
    0.77
    Activations Density 0.134%

    No Known Activations