© 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. 13459
    Prev
    Next
    INDEX
    Explanations

    text encodings that are likely unusual or corrupted

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 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
    enegger
    -1.09
     guiActiveUnfocused
    -0.84
    ORED
    -0.74
     Electronics
    -0.65
     dividing
    -0.65
    schild
    -0.65
     flash
    -0.64
    creen
    -0.64
     Conrad
    -0.64
     decomp
    -0.62
    POSITIVE LOGITS
    ģ
    1.31
    ¼
    1.29
    ¤
    1.27
    ´
    1.27
    ¬
    1.26
    ¢
    1.22
    ³
    1.21
    ²
    1.21
    ª
    1.21
    ¶
    1.21
    Activations Density 0.017%

    No Known Activations