© 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. 9-RES-JB
    11. 18630
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences requesting comments or reactions from entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases and contexts involving official comments or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Empires
    -0.75
     countered
    -0.75
    hops
    -0.71
     alike
    -0.68
    soever
    -0.68
     furthermore
    -0.68
     therefore
    -0.67
     Ships
    -0.67
    Europe
    -0.66
    Faith
    -0.66
    POSITIVE LOGITS
     discrepancy
    1.21
     incident
    1.20
     situation
    1.17
     possibility
    1.16
     latest
    1.15
     specifics
    1.12
     findings
    1.11
     extent
    1.08
     validity
    1.05
     significance
    1.02
    Activations Density 0.282%

    No Known Activations