© 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. 24124
    Prev
    Next
    INDEX
    Explanations

    words related to challenges or obstacles that need to be overcome

    oai_token-act-pair · gpt-3.5-turbo

    references to obstacles or challenges

    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
    orp
    -0.74
    ersive
    -0.74
    usage
    -0.73
    akening
    -0.73
    oral
    -0.71
    erent
    -0.71
    ensive
    -0.70
    Interstitial
    -0.70
    amed
    -0.69
    obar
    -0.69
    POSITIVE LOGITS
     hurdles
    1.44
     hurdle
    1.42
     obstacles
    0.84
    hill
    0.81
     obstacle
    0.80
     waivers
    0.78
    SourceFile
    0.78
     hoops
    0.77
     barriers
    0.73
     hurd
    0.72
    Activations Density 0.007%

    No Known Activations