© 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. 12067
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms like "Komplete", "Korn", "Kwakwaka'wakw", and "Angry Men"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Kom" and its variations

    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
    STATE
    -0.78
    ++++++++++++++++
    -0.76
    Deal
    -0.72
     Reaper
    -0.72
    Obama
    -0.70
     Prayer
    -0.65
    IBLE
    -0.63
    ب
    -0.63
    Charge
    -0.63
    Rah
    -0.63
    POSITIVE LOGITS
    atsu
    1.04
     Kw
    1.03
    arna
    0.83
    orea
    0.83
    odo
    0.80
     Yen
    0.80
    itsch
    0.79
    oji
    0.78
     Kom
    0.78
    inski
    0.77
    Activations Density 0.013%

    No Known Activations