© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12665
    Prev
    Next
    INDEX
    Explanations

    specific structured patterns of text featuring symbols and names

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or unusual characters

    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
     semic
    -0.64
    çīĪ
    -0.62
     RAD
    -0.61
     Syd
    -0.59
     polyg
    -0.59
     interf
    -0.58
    anwhile
    -0.58
     domestic
    -0.57
    çĶ°
    -0.56
     guiActiveUnfocused
    -0.55
    POSITIVE LOGITS
    ¬
    0.85
    ¡
    0.82
    ¼
    0.80
    £
    0.80
    Ń
    0.79
    Ĭ
    0.78
    º
    0.78
    Ĵ
    0.77
    ¹
    0.76
    Ī
    0.76
    Activations Density 0.414%

    No Known Activations