© 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. 0-RES-JB
    11. 7729
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    representations of a specific branding or product category, particularly marked by the repetition of "XX" and derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pik
    -0.86
     Gul
    -0.72
     pil
    -0.71
     takeaway
    -0.68
     Cree
    -0.67
     Crusher
    -0.66
     Cod
    -0.65
     Cu
    -0.65
     Ni
    -0.64
     Nav
    -0.64
    POSITIVE LOGITS
    XX
    3.85
    XXX
    2.87
     XX
    2.75
    xx
    2.35
     XXX
    2.26
    xxx
    2.16
    XXXX
    1.74
     xx
    1.68
    xxxx
    1.50
     XV
    1.44
    Activations Density 0.043%

    No Known Activations