INDEX

Explanations

contextual clues related to product reviews and customer experiences

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

Jeografia

-0.58



-0.55

DllImport

-0.55

 Roskov

-0.54

 cherchés

-0.53

 http

-0.50

http

-0.50

mbggenerated

-0.50

-0.48

mpotent

-0.47

POSITIVE LOGITS

 iſt

0.62

 článku

0.60

 Jefus

0.59

aarrggbb

0.59

ENEFITS

0.58

hies

0.56

ufige

0.56

CELLANEOUS

0.55

 tips

0.55

 sentinel

0.55

Activations Density 0.054%

contextual clues related to product reviews and customer experiences

No Comments

No Known Activations