© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 954
    Prev
    Next
    INDEX
    Explanations

    the character '²'

    oai_token-act-pair · gpt-4-turbo

    number combinations and some special characters

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols potentially indicating encoding issues or non-standard text

    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
    nesota
    -0.84
    isner
    -0.79
    NetMessage
    -0.79
    ynthesis
    -0.79
    sembly
    -0.78
    ebus
    -0.78
    pocket
    -0.78
    essing
    -0.76
    versions
    -0.74
    ession
    -0.73
    POSITIVE LOGITS
    ²
    1.04
    ³
    1.01
    ¡
    1.01
    ł
    0.97
    ãĥ¼ãĥ
    0.92
    ´
    0.91
    »
    0.85
    ãĤ§
    0.83
    ãĤ«
    0.83
    ¹
    0.82
    Activations Density 0.006%

    No Known Activations