© 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. 10-RES-JB
    11. 9897
    Prev
    Next
    INDEX
    Explanations

    words related to growth or increase in intensity

    oai_token-act-pair · gpt-3.5-turbo

    words related to growth or increase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.79
     Mub
    -0.78
    pta
    -0.74
    querque
    -0.73
     Rouge
    -0.72
    asures
    -0.69
    urn
    -0.68
    issors
    -0.65
    isites
    -0.64
    orneys
    -0.63
    POSITIVE LOGITS
     exponentially
    1.21
     stronger
    1.12
     pains
    1.03
     louder
    1.01
     tremendously
    0.97
     steadily
    0.96
     bigger
    0.95
     enormously
    0.93
     stale
    0.93
     accustomed
    0.92
    Activations Density 0.037%

    No Known Activations