© 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. 17110
    Prev
    Next
    INDEX
    Explanations

    words related to recovery and improvement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "recovery" in various contexts

    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
    ãĥ¥
    -0.82
    OPA
    -0.81
    ãĤ°
    -0.81
    seless
    -0.80
    ks
    -0.73
    ãĥ£
    -0.73
    âĸ¬âĸ¬
    -0.70
    nit
    -0.69
    fle
    -0.67
    ر
    -0.67
    POSITIVE LOGITS
    ilitating
    0.80
    ilitation
    0.77
    ary
    0.71
    algia
    0.70
     underway
    0.68
     efforts
    0.66
     recovery
    0.66
     mindset
    0.65
    uberty
    0.64
    ees
    0.64
    Activations Density 0.034%

    No Known Activations