© 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. 7-RES-JB
    11. 3880
    Prev
    Next
    INDEX
    Explanations

    words containing specific special characters (e.g., Å)

    oai_token-act-pair · gpt-3.5-turbo

    the character 'Å'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commodore
    -0.74
    iflower
    -0.70
     Sidd
    -0.69
    builders
    -0.67
    ITNESS
    -0.66
    WARD
    -0.66
    bro
    -0.65
     Leilan
    -0.63
     DMV
    -0.61
     combustion
    -0.61
    POSITIVE LOGITS
    ĵ
    1.25
    ĭ
    1.25
    ¾
    1.22
    ı
    1.19
    ¼
    1.18
    ½
    1.17
    Ĵ
    1.15
    Ī
    1.14
    ł
    1.14
    ¸
    1.13
    Activations Density 0.018%

    No Known Activations