© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12400
    Prev
    Next
    INDEX
    Explanations

    mentions of the geographical location "Black Sea"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Black" and its various contexts

    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
    PsyNetMessage
    -0.98
     sidx
    -0.84
    icular
    -0.80
    DCS
    -0.80
    =-=-=-=-
    -0.77
    OPLE
    -0.76
    _-
    -0.76
    rative
    -0.75
    igslist
    -0.75
    olate
    -0.74
    POSITIVE LOGITS
    berry
    1.16
    smith
    1.07
    hawk
    1.04
    feet
    1.01
    bird
    1.01
    moon
    0.97
    jack
    0.97
    wings
    0.96
     Panther
    0.95
    ened
    0.92
    Activations Density 0.023%

    No Known Activations