© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 7688
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation of future interactions or reunions

    oai_token-act-pair · gpt-3.5-turbo

    references to engagement or addressing an audience directly

    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
    ¿½
    -0.60
    SPONSORED
    -0.60
    umes
    -0.59
    sense
    -0.58
    otine
    -0.58
    ignore
    -0.54
    UID
    -0.53
    ceivable
    -0.53
     Slave
    -0.53
    ĨĴ
    -0.52
    POSITIVE LOGITS
     tomorrow
    0.93
     guys
    0.89
     soon
    0.87
     next
    0.83
     later
    0.76
    stanbul
    0.76
    uesday
    0.76
    next
    0.76
    ldon
    0.75
    aturday
    0.72
    Activations Density 0.055%

    No Known Activations