© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to communication and understanding

    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
    escription
    -0.69
    iversary
    -0.68
    estern
    -0.67
    Synopsis
    -0.65
    aug
    -0.64
     Announce
    -0.61
     Celebr
    -0.59
     teaser
    -0.59
     Released
    -0.58
    iatus
    -0.58
    POSITIVE LOGITS
     jurisdiction
    0.83
     disadvantage
    0.82
     limits
    0.80
     limitations
    0.78
     limit
    0.77
     disadvantages
    0.75
     impossibility
    0.74
     latitude
    0.72
     constraints
    0.71
     limitation
    0.71
    Activations Density 1.580%

    No Known Activations