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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 7601
    Prev
    Next
    INDEX
    Explanations

    words related to plundering or theft

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political structures or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prescott
    -0.63
     avail
    -0.61
     PAL
    -0.60
    relevant
    -0.58
     incre
    -0.58
     allegiance
    -0.56
    /-
    -0.55
     Elf
    -0.55
     Tara
    -0.53
     regard
    -0.53
    POSITIVE LOGITS
    ocene
    1.04
    encia
    1.02
    iar
    0.92
    iband
    0.87
    inational
    0.84
    estyles
    0.84
    erer
    0.82
    enced
    0.79
    erers
    0.78
    ocrats
    0.75
    Activations Density 0.056%

    No Known Activations