© 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. 0-RES-JB
    11. 22220
    Prev
    Next
    INDEX
    Explanations

    the specific word "Bastard" within the text

    oai_token-act-pair · gpt-3.5-turbo

    the term "Bastard" in various contexts, particularly relating to beer or personality references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.72
    idth
    -0.72
    ĸļ
    -0.67
    idium
    -0.66
     subsequ
    -0.66
    perty
    -0.63
    ãĥ³ãĤ¸
    -0.63
    ternity
    -0.62
    Ħ¢
    -0.62
    ech
    -0.62
    POSITIVE LOGITS
    mart
    1.02
    Mart
    0.72
    cent
    0.70
     Guns
    0.66
    atana
    0.65
    Fake
    0.65
     Swords
    0.65
     Gloves
    0.65
    Po
    0.64
     Gale
    0.64
    Activations Density 0.000%

    No Known Activations