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. 8246
    Prev
    Next
    INDEX
    Explanations

    the name "Rab" and words related to legal defense organizations like NAACP

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or entities

    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
    fulness
    -0.92
    aled
    -0.89
    kson
    -0.86
    borg
    -0.84
    ivers
    -0.82
    arlane
    -0.81
    ery
    -0.80
    achusetts
    -0.80
    ers
    -0.79
    opal
    -0.79
    POSITIVE LOGITS
    âķIJâķIJ
    0.88
    PsyNetMessage
    0.78
    BIP
    0.72
     aspirin
    0.68
    ãĤ¡
    0.66
    ¶æ
    0.66
     Juliet
    0.65
    ollah
    0.65
     subp
    0.61
     laureate
    0.59
    Activations Density 0.073%

    No Known Activations