© 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. 4-RES-JB
    11. 10230
    Prev
    Next
    INDEX
    Explanations

    terms related to increasing something or taking it to a higher level

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "ante" or raises in stakes

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

    No Comments

    Negative Logits
    ularity
    -0.82
    izabeth
    -0.80
    ician
    -0.78
    bies
    -0.74
    Streamer
    -0.72
    ansas
    -0.72
    ary
    -0.71
    isms
    -0.71
    esian
    -0.71
    ota
    -0.70
    POSITIVE LOGITS
     ante
    1.07
    cend
    0.78
    vent
    0.76
    phrine
    0.75
     Tec
    0.75
    hot
    0.72
    vention
    0.68
     bunny
    0.67
     quint
    0.67
     Ruff
    0.65
    Activations Density 0.028%

    No Known Activations