INDEX

Explanations

indicators of authenticity and truthfulness in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

InjectAttribute

-1.07

 <>",

-0.91

 ModelExpression

-0.85

 ſche

-0.83

 piaggio

-0.82

Jeografia

-0.81

 alphabetically

-0.81

 ContentValues

-0.81

 whofe

-0.78

sidemargin

-0.78

POSITIVE LOGITS

 real

1.22

 genuine

1.09

 true

1.03

真正的

0.98

real

0.98

 truly

0.97

真正

0.96

 REAL

0.96

 Real

0.93

 echte

0.93

Activations Density 0.256%

indicators of authenticity and truthfulness in descriptions

No Comments

No Known Activations