INDEX

Explanations

statistical terms related to variance and confidence intervals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nek

-0.53

bry

-0.52

 passage

-0.47

lants

-0.45

Fel

-0.44

 Sweet

-0.43

 Bellamy

-0.43

 Bryant

-0.43

nij

-0.42

POSITIVE LOGITS

MessageTagHelper

0.81

crollView

0.80

 '\\;'

0.78

tvguidetime

0.77

 variance

0.75

ISupport

0.75

ArrowToggle

0.75

 covariance

0.75

enderror

0.74

InputBorder

0.73

Activations Density 0.768%

statistical terms related to variance and confidence intervals

No Comments

No Known Activations