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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 6758
    Prev
    Next
    INDEX
    Explanations

    references to spreading rumors or unfounded claims

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rumors or accusations

    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
    atre
    -0.72
    borg
    -0.66
    pling
    -0.65
    onomic
    -0.62
    ocks
    -0.62
    ien
    -0.61
    ouk
    -0.61
    osures
    -0.61
    waters
    -0.61
    ey
    -0.60
    POSITIVE LOGITS
     accompanies
    0.98
    soever
    0.92
     arose
    0.87
     preceded
    0.84
     they
    0.77
     contradicts
    0.77
    ©¶æ
    0.76
     accompanied
    0.75
     contradicted
    0.73
     surrounds
    0.72
    Activations Density 0.192%

    No Known Activations