© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 7836
    Prev
    Next
    INDEX
    Explanations

    the name "Riley" with varied and sometimes lower activations for related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and references that suggest notable discussions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    racuse
    -0.93
    ablishment
    -0.92
    ertodd
    -0.92
    ÑĮ
    -0.86
    ropolitan
    -0.85
    odon
    -0.82
    aminer
    -0.82
    taining
    -0.80
    ansas
    -0.77
    tainment
    -0.74
    POSITIVE LOGITS
     Riley
    0.76
    otti
    0.70
    caster
    0.68
    ulus
    0.68
     patched
    0.66
    ochet
    0.66
     bonded
    0.66
     Plague
    0.65
    senal
    0.64
     eternal
    0.63
    Activations Density 0.012%

    No Known Activations