© 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. 5557
    Prev
    Next
    INDEX
    Explanations

    words related to prolificness or productivity

    oai_token-act-pair · gpt-3.5-turbo

    words related to prolific output or creativity

    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
    ummies
    -0.75
    strap
    -0.71
     Dign
    -0.67
    PRES
    -0.66
    ift
    -0.65
    ĪĴ
    -0.65
    ATHER
    -0.63
    Doctors
    -0.60
     Disability
    -0.59
     Rite
    -0.58
    POSITIVE LOGITS
     prolific
    1.10
    uously
    0.91
    ally
    0.91
    ulously
    0.81
    odox
    0.81
    lisher
    0.79
    iously
    0.79
    icity
    0.78
    ious
    0.78
    atoes
    0.76
    Activations Density 0.003%

    No Known Activations