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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9381
    Prev
    Next
    INDEX
    Explanations

    mentions of teenagers or events related to teenagers

    oai_token-act-pair · gpt-3.5-turbo

    references to teenagers and their experiences

    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
    veyard
    -0.98
    igslist
    -0.82
    ichick
    -0.78
    anwhile
    -0.77
    andum
    -0.77
    vernment
    -0.76
    cemic
    -0.74
    ×Ļ×
    -0.72
    choes
    -0.71
    UTERS
    -0.70
    POSITIVE LOGITS
    aged
    1.05
    ishly
    0.92
    uates
    0.90
    Teen
    0.85
    ety
    0.84
    y
    0.77
    agers
    0.75
    Nick
    0.75
    iest
    0.72
    ish
    0.71
    Activations Density 0.008%

    No Known Activations