INDEX

Explanations

phrases related to comparison and causation

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

 ويكيپيديا

-1.00

Efq

-0.96

ſelf

-0.84

évaluateur

-0.81

 itſelf

-0.79

 myſelf

-0.78

TypedDataSet

-0.76

 initComponents

-0.76

 ſeveral

-0.76

expandindo

-0.76

POSITIVE LOGITS

<bos>

0.59

0.53

th

0.49

cestershire

0.49

↵↵

0.48

di

0.47

ashian

0.46

#![

0.46

Int

0.45

Activations Density 1.495%

phrases related to comparison and causation

No Comments

No Known Activations