INDEX

Explanations

numerical data and measurement related to specificity and effectiveness

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.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

ANS

-0.38

 ورد

-0.38

Legături

-0.38

 getopt

-0.35

NIS

-0.35

рного

-0.35

 Anſ

-0.34

 почи

-0.34

Novel

-0.34

ابراین

-0.34

POSITIVE LOGITS

百分之

1.16

百分

1.14

 wholly

1.12

 entirely

1.10

 totally

1.09

 completely

1.07

 fully

1.02

 sepenuhnya

1.02

 hundert

1.02

 hundred

0.96

Activations Density 0.246%

numerical data and measurement related to specificity and effectiveness

No Comments

No Known Activations