© 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. 9-RES-JB
    11. 15347
    Prev
    Next
    INDEX
    Explanations

    phrases related to software technology and programming

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or positive sentiment in the context of software or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.78
    aukee
    -0.75
    raped
    -0.75
    Woman
    -0.74
    Crime
    -0.73
     arrested
    -0.68
    MpServer
    -0.68
    ocide
    -0.68
     raped
    -0.67
    crime
    -0.67
    POSITIVE LOGITS
     usability
    1.09
     developers
    1.06
     Microsoft
    0.98
     Developers
    0.98
     Mozilla
    0.96
     OEM
    0.93
     startups
    0.93
     designers
    0.92
     advancements
    0.92
     devs
    0.92
    Activations Density 0.656%

    No Known Activations