© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    references to geographical places or regions

    oai_token-act-pair · gpt-3.5-turbo

    the prepositions "At" and "And" indicating location and conjunctions

    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
    etheless
    -0.71
    terday
    -0.66
     dece
    -0.62
     suppressed
    -0.60
     nose
    -0.60
     nails
    -0.59
     heel
    -0.58
     suspic
    -0.58
    EStreamFrame
    -0.57
     writ
    -0.57
    POSITIVE LOGITS
    oran
    0.84
    alf
    0.84
    alys
    0.84
    aman
    0.81
    ussie
    0.80
    grid
    0.79
    vent
    0.78
    opath
    0.77
    itialized
    0.77
    slaught
    0.75
    Activations Density 0.137%

    No Known Activations