© 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. 6-RES-JB
    11. 12843
    Prev
    Next
    INDEX
    Explanations

    mentions of injections or injecting

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of injections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.81
    ries
    -0.80
    HCR
    -0.79
    ŃĶ
    -0.76
    Ü
    -0.74
    kees
    -0.73
    mpeg
    -0.72
    ģ«
    -0.70
    GE
    -0.70
    functional
    -0.69
    POSITIVE LOGITS
     injected
    0.98
     injection
    0.97
     injecting
    0.96
     injections
    0.95
     inject
    0.93
     molded
    0.90
    ysis
    0.75
     venom
    0.73
     dose
    0.73
     pumps
    0.72
    Activations Density 0.024%

    No Known Activations