© 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. 1-RES-JB
    11. 5556
    Prev
    Next
    INDEX
    Explanations

    words related to "pent" or "penthouse"

    oai_token-act-pair · gpt-3.5-turbo

    references to "pent" or "Pent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.74
     Referred
    -0.70
    BILITY
    -0.66
    ONSORED
    -0.65
     Milo
    -0.63
    ISSION
    -0.62
     Hitman
    -0.62
     Benef
    -0.61
     Malf
    -0.61
     Mahar
    -0.59
    POSITIVE LOGITS
     pent
    1.53
    iple
    0.91
    agon
    0.90
    agonal
    0.88
    etr
    0.86
    raph
    0.84
    agons
    0.82
    obar
    0.80
     tet
    0.78
    alogue
    0.78
    Activations Density 0.013%

    No Known Activations