© 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. 2-RES-JB
    11. 4546
    Prev
    Next
    INDEX
    Explanations

    mentions in a text where someone declines to comment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declined" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.86
    Offline
    -0.80
    agate
    -0.79
    =-=-=-=-=-=-=-=-
    -0.72
    neys
    -0.70
    Clean
    -0.69
    ICAN
    -0.67
    Pur
    -0.66
    ãĤ·ãĥ£
    -0.66
    enfranch
    -0.64
    POSITIVE LOGITS
     declines
    0.82
     declined
    0.79
     miser
    0.74
     escal
    0.73
     Krug
    0.73
    yip
    0.69
     confir
    0.69
     warr
    0.68
    yss
    0.66
     hes
    0.65
    Activations Density 0.009%

    No Known Activations