Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9819
    Prev
    Next
    INDEX
    Explanations

    various instances of the word "fear" at different levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    mentions and variations of the word "fear."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nice
    -0.82
    arkable
    -0.68
    odore
    -0.68
    afort
    -0.67
    ilib
    -0.64
    cially
    -0.63
    anmar
    -0.63
    urgy
    -0.63
    area
    -0.63
    arch
    -0.63
    POSITIVE LOGITS
    lessly
    1.29
    lessness
    1.29
    mong
    1.28
    fulness
    1.06
    fully
    0.97
    crow
    0.96
     lest
    0.89
    warts
    0.84
     Mong
    0.83
    wart
    0.81
    Activations Density 0.032%

    No Known Activations