© 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. 1-RES-JB
    11. 16258
    Prev
    Next
    INDEX
    Explanations

    character sequences that incorporate special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stro
    -0.77
    alos
    -0.74
    stroke
    -0.73
    ashtra
    -0.69
     GOODMAN
    -0.67
    itar
    -0.67
    raviolet
    -0.65
    rified
    -0.64
    espie
    -0.63
    cair
    -0.62
    POSITIVE LOGITS
    ¬¼
    1.35
    ë
    1.34
    ¶ħ
    1.17
    Ĥ
    1.09
     ë
    1.08
    Ŀ
    1.04
    į
    1.03
    Ķ
    1.02
    ¯
    1.02
    ¹
    1.02
    Activations Density 0.006%

    No Known Activations