INDEX

Explanations

segments that indicate the start of a new section or passage in 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 @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ItemBackground

-0.69

 jsPsych

-0.69

 Shakspeare

-0.61

 صوتيه

-0.61

MessageTagHelper

-0.58

fvar

-0.56

ArrowToggle

-0.56

StructEnd

-0.55

 Lordships

-0.55

vician

-0.54

POSITIVE LOGITS

 nahilalakip

0.86

 AssemblyCulture

0.67

 colspan

0.62

Примечания

0.55

__(/*!

0.55

 nakalista

0.55

GEBURTSDATUM

0.54

("")]

0.54

 dich

0.53

Diwedd

0.53

Activations Density 0.098%

segments that indicate the start of a new section or passage in the text

No Comments

No Known Activations