© 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. 1627
    Prev
    Next
    INDEX
    Explanations

    the specific name "Pen" as part of a word

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Pen" and its variations, likely referring to a specific person or character

    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
    enance
    -0.76
    ����
    -0.67
     mono
    -0.63
    ````
    -0.60
     Marxism
    -0.59
    tt
    -0.59
    ģĸ
    -0.59
    avez
    -0.58
     Benef
    -0.58
     sexes
    -0.58
    POSITIVE LOGITS
    cil
    1.55
    insula
    1.45
    itent
    1.39
    elope
    1.39
    alties
    1.34
    ultimate
    1.25
    cill
    1.07
    nington
    1.05
    ning
    1.05
    manship
    0.99
    Activations Density 0.019%

    No Known Activations