INDEX

Explanations

phrases related to actions or processes that involve taking, utilizing, or analyzing data

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

 houſe

-0.88

 purpoſe

-0.86

 itſelf

-0.80

 myſelf

-0.78

 raiſ

-0.78

IBLIO

-0.78

 himſelf

-0.77

ſelves

-0.76

 Theſe

-0.75

 Houſe

-0.75

POSITIVE LOGITS

 taken

1.10

Taking

1.08

 Taking

1.08

 taking

1.08

 take

1.07

 takes

0.99

take

0.96

taken

0.96

 Take

0.95

 Taken

0.93

Activations Density 0.159%

phrases related to actions or processes that involve taking, utilizing, or analyzing data

No Comments

No Known Activations