INDEX

Explanations

articles and quantifiers in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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



-1.24

tvguidetime

-1.16

 nahilalakip

-1.13

 '\\;'

-1.09

 Signalez

-1.08

TagMode

-1.07

 Anſ

-1.07

 Diſ

-1.03

 Reſ

-1.03

 ſind

-1.02

POSITIVE LOGITS

0.89

0.66

0.60

 back

0.60

0.59

am

0.58

an

0.57

“

0.57

Activations Density 0.260%

articles and quantifiers in a text

No Comments

No Known Activations