© 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. 8-RES-JB
    11. 20188
    Prev
    Next
    INDEX
    Explanations

    dollar amounts in various currencies

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated numerical values, particularly those related to loss or financial estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rein
    -0.75
     Cros
    -0.73
     ART
    -0.73
     Unch
    -0.65
     behav
    -0.65
     RH
    -0.64
     hots
    -0.63
     Bram
    -0.63
     CJ
    -0.62
     Orb
    -0.61
    POSITIVE LOGITS
    000
    1.76
    500
    1.24
    00
    1.23
    0000
    1.15
    001
    1.13
    200
    1.09
    600
    1.06
    0002
    1.06
    300
    1.06
    1000
    1.05
    Activations Density 0.059%

    No Known Activations