© 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. 20146
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases beginning with "by," indicating attribution or causation

    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
    ounter
    -0.65
    ptions
    -0.64
     digs
    -0.63
    istan
    -0.62
     ILCS
    -0.61
    earable
    -0.59
    ptive
    -0.58
    imal
    -0.58
    stadt
    -0.54
    ylum
    -0.53
    POSITIVE LOGITS
    products
    1.28
     virtue
    1.16
    akuya
    1.07
    laws
    1.03
    product
    1.02
     implication
    1.01
    catch
    0.96
    gone
    0.96
     extension
    0.91
     default
    0.86
    Activations Density 0.083%

    No Known Activations