© 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. 24114
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals named "Rat" and their associated contexts or mentions in a dataset

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rat" and its variations

    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
    PLIED
    -0.71
    FAULT
    -0.70
     compr
    -0.66
    OURCE
    -0.65
     Catalonia
    -0.64
     Cyprus
    -0.64
    ¬¼
    -0.63
    «ĺ
    -0.62
     distributed
    -0.60
    conservancy
    -0.60
    POSITIVE LOGITS
    chet
    1.33
     Rat
    1.19
    Rat
    1.02
    cliffe
    1.01
     Rats
    0.90
    rat
    0.88
    atos
    0.85
    ombat
    0.84
    ilda
    0.83
    gey
    0.83
    Activations Density 0.006%

    No Known Activations