© 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. 11-RES-JB
    11. 22456
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinion expressions and statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and conjunction usage in complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ickers
    -0.65
    erick
    -0.64
    erd
    -0.62
    BRE
    -0.62
    eret
    -0.61
    eln
    -0.60
    isch
    -0.60
    ophon
    -0.60
    ilic
    -0.59
    ourses
    -0.58
    POSITIVE LOGITS
     Including
    1.37
    except
    1.36
     including
    1.33
    including
    1.28
     regardless
    1.24
     except
    1.24
     INCLUD
    1.20
     irrespective
    1.20
     anytime
    1.11
    every
    1.10
    Activations Density 0.433%

    No Known Activations