© 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. 3-RES-JB
    11. 10701
    Prev
    Next
    INDEX
    Explanations

    words related to obstacles or hindrances

    oai_token-act-pair · gpt-3.5-turbo

    references to setbacks or failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    och
    -0.77
    umption
    -0.75
    ophysical
    -0.74
    tein
    -0.74
    ophers
    -0.72
    erville
    -0.69
    cise
    -0.67
    atorial
    -0.66
    ergy
    -0.66
    rouse
    -0.65
    POSITIVE LOGITS
     setbacks
    1.28
     setback
    1.11
     adversity
    0.84
     Delay
    0.75
     headaches
    0.72
     defeats
    0.72
     sidel
    0.70
     defeat
    0.70
     delays
    0.70
     derail
    0.69
    Activations Density 0.009%

    No Known Activations