© 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. 0-RES-JB
    11. 11289
    Prev
    Next
    INDEX
    Explanations

    terms related to data backup and recovery

    oai_token-act-pair · gpt-3.5-turbo

    references to backup systems or processes

    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
    ieties
    -0.72
    ieth
    -0.71
    okes
    -0.70
    igion
    -0.69
    enn
    -0.67
    lam
    -0.66
     Oriental
    -0.65
    agh
    -0.65
    Islamic
    -0.65
    omen
    -0.64
    POSITIVE LOGITS
     backup
    3.81
     backups
    3.30
     Backup
    2.63
     standby
    1.44
     contingency
    1.24
     redundancy
    1.23
     replacement
    1.18
     replacements
    1.15
     backend
    1.14
     clipboard
    1.12
    Activations Density 0.023%

    No Known Activations