© 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. 1-RES-JB
    11. 20218
    Prev
    Next
    INDEX
    Explanations

    years represented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    years or numerical references in the context of historical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aminer
    -0.78
     backfield
    -0.76
     millenn
    -0.73
     nomine
    -0.70
     stuffed
    -0.68
    igent
    -0.67
     cram
    -0.67
    istor
    -0.66
     shaved
    -0.66
     whipped
    -0.65
    POSITIVE LOGITS
    âĸĪâĸĪ
    1.11
    49
    1.10
    19
    1.10
    61
    1.08
    05
    1.01
    08
    1.00
    39
    1.00
    04
    0.99
    37
    0.99
    58
    0.98
    Activations Density 0.016%

    No Known Activations