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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1043
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rat", including both literal and metaphorical references

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rat" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.77
    Ļ½
    -0.76
    PLIED
    -0.73
    conservancy
    -0.69
    alach
    -0.69
     Cyprus
    -0.68
    «ĺ
    -0.65
     Catalonia
    -0.63
    irit
    -0.63
     Mandela
    -0.61
    POSITIVE LOGITS
    chet
    1.47
    che
    0.98
    ifiers
    0.91
    atos
    0.91
    ting
    0.91
    imilation
    0.91
    rice
    0.89
    cliffe
    0.87
    oxin
    0.86
    mone
    0.84
    Activations Density 0.014%

    No Known Activations