INDEX

Explanations

terms related to validation and confirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

########.

-0.60

 mcqueen

-0.58

WireFormatLite

-0.57

 tartalomajánló

-0.56

 commerciales

-0.51

awat

-0.50

 BoxDecoration

-0.49

 Wikimedijinoj

-0.49

 hypo

-0.48

 اک

-0.48

POSITIVE LOGITS

 verify

1.61

 confirm

1.60

 Verify

1.49

Verify

1.45

 Confirm

1.42

 confirming

1.31

 confirms

1.27

 verifying

1.23

 verifies

1.23

verify

1.19

Activations Density 0.125%

terms related to validation and confirmation

No Comments

No Known Activations