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. 0-RES-JB
    6. 22919
    Prev
    Next
    INDEX
    Explanations

    rumors or discussions indicating uncertain information or speculation

    oai_token-act-pair · gpt-3.5-turbo

    references to rumors and speculation

    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
     RESP
    -0.85
     Respons
    -0.77
    ised
    -0.67
    Labour
    -0.66
    ade
    -0.65
    arching
    -0.65
     £
    -0.65
     centre
    -0.64
    alys
    -0.64
    Const
    -0.63
    POSITIVE LOGITS
     rumors
    3.81
     rumor
    3.33
     rumours
    2.99
     rumored
    2.24
    Rum
    2.13
     gossip
    1.84
     Rum
    1.76
     speculation
    1.75
     whispers
    1.66
     legends
    1.38
    Activations Density 0.026%

    No Known Activations