INDEX

Explanations

terms related to bias in research and statistical estimation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

expandindo

-0.94

awtextra

-0.75

帖最后由

-0.74

Personensuche

-0.74

 nakalista

-0.70

Portale

-0.69

BeginContext

-0.66

 Boyce

-0.66

contentLoaded

-0.64

tslib

-0.64

POSITIVE LOGITS

 bias

1.83

 Bias

1.81

bias

1.54

Bias

1.53

 biases

1.39

 biased

1.31

biased

1.23

BIAS

1.15

biases

1.10

 leaning

0.95

Activations Density 0.171%

terms related to bias in research and statistical estimation

No Comments

No Known Activations