© 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. 10-RES-JB
    11. 12744
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data reporting and security

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reporting and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esides
    -0.79
    efully
    -0.65
    —"
    -0.64
     beforehand
    -0.63
     afterward
    -0.62
    Brit
    -0.62
    nat
    -0.62
    luster
    -0.60
    herer
    -0.60
     wherever
    -0.59
    POSITIVE LOGITS
     deprecated
    0.83
     async
    0.75
     ransomware
    0.73
     debian
    0.72
     systemd
    0.71
     airstrike
    0.71
     DMCA
    0.71
     malware
    0.71
     Abandon
    0.70
    orem
    0.70
    Activations Density 0.445%

    No Known Activations