INDEX

Explanations

terms related to estimating, estimates, or statistical predictions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

’

-0.85

“

-0.77

“

-0.72

-0.71

-0.68

</i>

-0.68

-0.65

-0.64

POSITIVE LOGITS

 Estimate

1.59

 Estimates

1.58

 estimates

1.57

 estimate

1.55

 estimat

1.55

Estimates

1.46

 ESTIM

1.42

 Esti

1.40

 Estimated

1.40

 Estimation

1.40

Activations Density 0.112%

terms related to estimating, estimates, or statistical predictions

No Comments

No Known Activations