© 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. 9-RES-JB
    11. 8790
    Prev
    Next
    INDEX
    Explanations

    sentences related to tasks or responsibilities performed by individuals within a community

    oai_token-act-pair · gpt-3.5-turbo

    references to technology and its impact on human interaction

    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
    é¾įå
    -0.69
    å·
    -0.67
    displayText
    -0.67
    igmat
    -0.66
    916
    -0.66
    isSpecialOrderable
    -0.66
    çīĪ
    -0.66
    Acknowled
    -0.62
    rero
    -0.61
    åĮ
    -0.60
    POSITIVE LOGITS
     themselves
    1.41
    selves
    0.98
     their
    0.98
     havoc
    0.86
     prey
    0.86
     mischief
    0.83
     us
    0.81
     THEIR
    0.78
     suck
    0.78
     souls
    0.76
    Activations Density 0.867%

    No Known Activations