© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    Skips or errors in the analysis provided

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to individual people's actions or attributes, particularly in a narrative or analytical context

    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
     Afric
    -0.86
    ctrl
    -0.80
    ãĤ´
    -0.74
    cent
    -0.70
     ASC
    -0.67
    AC
    -0.67
    194
    -0.64
    ufact
    -0.64
    ico
    -0.63
    Albert
    -0.63
    POSITIVE LOGITS
    EStreamFrame
    0.81
    DeliveryDate
    0.72
     Daughter
    0.72
    roxy
    0.71
    GoldMagikarp
    0.71
    VIDIA
    0.68
    rome
    0.68
     TAMADRA
    0.67
    onies
    0.66
    roth
    0.65
    Activations Density 0.545%

    No Known Activations