© 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. 6-RES-JB
    11. 24476
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters, possibly indicating a neuron looking for text in a specific language or character encoding

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.67
    aday
    -0.66
    theless
    -0.65
     guiActiveUnfocused
    -0.65
     Starr
    -0.63
    ãĥ¼ãĥĨ
    -0.63
    anwhile
    -0.62
    oleon
    -0.60
     Downing
    -0.60
    wagen
    -0.60
    POSITIVE LOGITS
    ¾
    1.41
    ¸
    1.30
    ł
    1.30
    ¿
    1.30
    º
    1.30
    ļ
    1.30
    ¡
    1.30
    ²
    1.29
    ij
    1.28
    ½
    1.27
    Activations Density 0.013%

    No Known Activations