© 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. 11-RES-JB
    11. 3573
    Prev
    Next
    INDEX
    Explanations

    specific mentions of devices or technical configurations

    oai_token-act-pair · gpt-3.5-turbo

    references to characters, monsters, and devices, particularly in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rontal
    -0.71
    culosis
    -0.70
    osate
    -0.69
    ķ
    -0.66
    tainment
    -0.63
    hyde
    -0.63
     Economist
    -0.63
    ĵ
    -0.61
    cknow
    -0.61
    nce
    -0.61
    POSITIVE LOGITS
    hips
    1.17
    '
    1.07
    paces
    1.07
     grouped
    1.06
     listed
    1.05
    hip
    1.02
     individually
    0.94
     composing
    0.94
    peed
    0.94
     residing
    0.93
    Activations Density 0.342%

    No Known Activations