INDEX

Explanations

words related to letters and written correspondence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

cassert

-0.54

 absoluto

-0.52

NORE

-0.51

 informée

-0.51

 كمان

-0.51

 Lovato

-0.50

 اسلامی

-0.49

 orgull

-0.48

 complete

-0.48

 खिला

-0.48

POSITIVE LOGITS

 letters

0.84

Letters

0.75

 Letters

0.74

bootstrapcdn

0.70

head

0.68

 LETTERS

0.68

 CreateTagHelper

0.68

SequentialGroup

0.68

 LETTER

0.66

letters

0.64

Activations Density 0.092%

words related to letters and written correspondence

No Comments

No Known Activations