© 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. 4594
    Prev
    Next
    INDEX
    Explanations

    words related to locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases or terms related to emotional connections and personal experiences

    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
    •Suppression Features Layer 8 GPT2 Small
    •Examples of different Logit Weight Distributions - GPT2 Small Layer 8
    Suppression Feature Example
    •Happy Hour
    Suppression feature example

    No Comments

    Negative Logits
    oval
    -1.01
    umen
    -1.01
    aris
    -0.99
    urer
    -0.96
    ctor
    -0.93
    ues
    -0.93
    oir
    -0.92
    ares
    -0.91
    inar
    -0.91
    eks
    -0.91
    POSITIVE LOGITS
     flush
    0.64
     bounce
    0.63
     retina
    0.63
     Hubble
    0.60
     wink
    0.60
     cliff
    0.59
     Colossus
    0.59
     Cinema
    0.58
     Broadcasting
    0.57
     Crush
    0.57
    Activations Density 0.367%

    No Known Activations