© 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. 2-RES-JB
    11. 12862
    Prev
    Next
    INDEX
    Explanations

    words related to medical assessments and procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ort."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.78
     Chimera
    -0.72
    ©¶æ
    -0.71
    pton
    -0.65
    ãĥ£
    -0.60
     Abyssal
    -0.58
     Berkeley
    -0.58
    CVE
    -0.58
     tall
    -0.57
     Cage
    -0.57
    POSITIVE LOGITS
    heast
    1.19
    ort
    1.06
    heastern
    1.00
    oad
    0.94
    gage
    0.93
    irect
    0.90
    nell
    0.88
    rait
    0.87
    itude
    0.85
    raits
    0.85
    Activations Density 0.006%

    No Known Activations