INDEX

Explanations

symbols or initial tokens that indicate the start of content or categories in a structured document

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

 nakalista

-0.54

getMin

-0.53

Migrations

-0.52

 createContext

-0.51

давно

-0.51

 prende

-0.51

 profondeur

-0.50

aaral

-0.50

 facultad

-0.50

Einzelnachweise

-0.50

POSITIVE LOGITS

 moment

0.76

 eventful

0.73

moment

0.68

localctx

0.66

 moments

0.61

 فرص

0.61

تقاوى

0.61

 periods

0.60

abetes

0.60

 time

0.59

Activations Density 0.281%

symbols or initial tokens that indicate the start of content or categories in a structured document

No Comments

No Known Activations