© 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. 0-RES-JB
    11. 22235
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person

    oai_token-act-pair · gpt-3.5-turbo

    the name "Anson" and variations or related mentions of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    locked
    -0.71
    âĶĢâĶĢ
    -0.71
    Poké
    -0.70
     Euph
    -0.66
     Dag
    -0.64
    ipop
    -0.63
    gets
    -0.63
    Tur
    -0.63
    Pokémon
    -0.62
    locks
    -0.61
    POSITIVE LOGITS
    anson
    4.36
    annie
    1.24
     Manson
    1.09
     Hanson
    1.02
     Swanson
    1.01
    onson
    1.00
    zynski
    0.98
    anto
    0.97
    anski
    0.90
    amba
    0.89
    Activations Density 0.017%

    No Known Activations