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. 9-RES-JB
    6. 467
    Prev
    Next
    INDEX
    Explanations

    terms related to political and social issues or events

    oai_token-act-pair · gpt-3.5-turbo

    commas in relation to significant statements or claims

    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
     extraord
    -0.70
    !'
    -0.64
    ominated
    -0.61
    mpire
    -0.61
     Noct
    -0.60
    ratulations
    -0.58
     !!
    -0.58
     Anarchy
    -0.58
    aimon
    -0.57
    çīĪ
    -0.57
    POSITIVE LOGITS
     noting
    1.27
     adding
    1.15
     citing
    1.09
     stressing
    1.03
     implying
    0.88
    including
    0.88
    particularly
    0.87
     namely
    0.87
     including
    0.87
     although
    0.86
    Activations Density 0.348%

    No Known Activations