© 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. 1-RES-JB
    11. 5456
    Prev
    Next
    INDEX
    Explanations

    descriptions of prosperous or successful situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to growth and success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifi
    -0.82
     PUR
    -0.73
     restraint
    -0.71
    endment
    -0.69
    nic
    -0.68
    issors
    -0.68
    agnetic
    -0.65
    OPE
    -0.64
    inen
    -0.61
    meal
    -0.61
    POSITIVE LOGITS
     booming
    0.89
     thriving
    0.87
     flourishing
    0.79
     entreprene
    0.78
     vibrant
    0.75
    interstitial
    0.74
    iterranean
    0.71
     bustling
    0.70
     burgeoning
    0.70
     anew
    0.69
    Activations Density 0.013%

    No Known Activations