© 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. 8-RES-JB
    6. 18474
    Prev
    Next
    INDEX
    Explanations

    strings of characters that do not form any coherent phrases or meaningful words

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commodore
    -0.71
    wards
    -0.70
     DMV
    -0.65
    iflower
    -0.64
     Carib
    -0.62
    ITNESS
    -0.60
    WARD
    -0.59
     Sidd
    -0.59
     Quadro
    -0.58
    waves
    -0.58
    POSITIVE LOGITS
    ¼
    1.23
    Ĵ
    1.22
    ¾
    1.21
    ı
    1.20
    ł
    1.20
    ¸
    1.19
    ½
    1.18
    Į
    1.18
    ĭ
    1.17
    ģ
    1.14
    Activations Density 0.028%

    No Known Activations