INDEX

Explanations

numerical data and values within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 seven

-1.02

six

-1.01

Six

-0.96

 Seven

-0.89

six

-0.86

seven

-0.84

 SEVEN

-0.83

SIX

-0.81

Six

-0.81

 eight

-0.81

POSITIVE LOGITS

 terceiro

0.60

 tercero

0.57

 terzo

0.52

 third

0.52

 troisième

0.50

 Third

0.49

Third

0.48

 AssemblyProduct

0.48

 cardíaca

0.47

 третье

0.47

Activations Density 0.316%

numerical data and values within the text

No Comments

No Known Activations