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. 21981
    Prev
    Next
    INDEX
    Explanations

    email communications

    oai_token-act-pair · gpt-3.5-turbo

    subjects and topics related to updates or status reports

    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
     honoured
    -0.88
     nurt
    -0.83
     pioneering
    -0.78
     Mehran
    -0.77
     celebrated
    -0.77
     pioneer
    -0.77
     renowned
    -0.76
    ustomed
    -0.75
     indigenous
    -0.75
     glamorous
    -0.75
    POSITIVE LOGITS
    Either
    0.99
    ???
    0.89
    maybe
    0.88
    _>
    0.88
     Nope
    0.87
    Assuming
    0.87
     dunno
    0.87
    :(
    0.86
     uh
    0.83
    )?
    0.82
    Activations Density 1.221%

    No Known Activations