© 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. 22428
    Prev
    Next
    INDEX
    Explanations

    announcements or statements of commitment

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate official announcements or declarations

    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
    ecd
    -0.82
     Explan
    -0.74
     perception
    -0.72
     understandable
    -0.69
     contrasts
    -0.68
     inexper
    -0.67
     adject
    -0.66
     brightness
    -0.64
     eloqu
    -0.64
     sophistication
    -0.64
    POSITIVE LOGITS
     indeed
    0.84
     officially
    0.78
     partnered
    0.70
    iatus
    0.70
     embark
    0.70
    soon
    0.69
     finally
    0.69
     postpone
    0.68
     retiring
    0.67
     hiatus
    0.65
    Activations Density 0.441%

    No Known Activations