© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14566
    Prev
    Next
    INDEX
    Explanations

    years with significant historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and notable events associated with those years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.67
    ulz
    -0.64
    ndra
    -0.61
    awed
    -0.58
    EStreamFrame
    -0.58
    hop
    -0.57
    erate
    -0.57
    folio
    -0.57
    zzle
    -0.56
     kin
    -0.56
    POSITIVE LOGITS
    -'
    0.88
     ILCS
    0.80
    oslov
    0.77
     Minutes
    0.76
    1966
    0.74
    sburg
    0.72
    å¹
    0.72
    rpm
    0.71
    1968
    0.70
    1963
    0.70
    Activations Density 0.066%

    No Known Activations