INDEX

Explanations

elements of dialogue or punctuation in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

Tikang

-0.90

SharedDtor

-0.80

ertale

-0.77

 Wiktionnaire

-0.77

RetentionPolicy

-0.77

AxisAlignment

-0.75

 BoxFit

-0.73

Viki

-0.73

.*")]

-0.73

WriteTagHelper

-0.72

POSITIVE LOGITS

 that

0.57

0.52

>{@

0.50

↵↵

0.46

0.45

 seems

0.44

 quite

0.44

…

0.44

Activations Density 0.086%

elements of dialogue or punctuation in text

No Comments

No Known Activations