© 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. 4-RES-JB
    11. 3630
    Prev
    Next
    INDEX
    Explanations

    the term "t9" occurring in a variety of contexts within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 't'

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

    No Comments

    Negative Logits
     tremend
    -0.86
     resil
    -0.84
     behavi
    -0.82
    £ı
    -0.81
     mosqu
    -0.80
     destro
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    ĪĴ
    -0.73
     actionGroup
    -0.73
     hemor
    -0.73
    POSITIVE LOGITS
    ribute
    1.15
    ractor
    1.15
    ruck
    1.14
    ract
    1.08
    asks
    1.07
    iful
    1.07
    ween
    1.07
    ronics
    1.06
    uple
    1.04
    olkien
    1.03
    Activations Density 0.089%

    No Known Activations