© 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. 2-RES-JB
    11. 24054
    Prev
    Next
    INDEX
    Explanations

    words related to unusual or out-of-the-ordinary situations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "freak" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adr
    -0.82
    ournal
    -0.80
    eger
    -0.74
    arta
    -0.74
    ea
    -0.71
    rity
    -0.68
    sein
    -0.67
    dated
    -0.65
    akespeare
    -0.64
    atana
    -0.64
    POSITIVE LOGITS
    ishly
    1.18
    ously
    0.96
    fuck
    0.82
     freak
    0.81
    istically
    0.80
    ulously
    0.78
    onom
    0.78
    bum
    0.76
    holes
    0.75
    hole
    0.74
    Activations Density 0.010%

    No Known Activations