INDEX

Explanations

references to crashes or related failures in various contexts

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

CloseOperation

-0.65

 contienen

-0.56

SerializeField

-0.56

 kaynağından

-0.55

fritt

-0.53

afone

-0.52

 contiennent

-0.50

entingan

-0.50

 aloft

-0.49

omla

-0.49

POSITIVE LOGITS

 Speak

1.00

Speak

0.99

 speak

0.92

 push

0.91

push

0.90

speak

0.89

 Push

0.88

Pushing

0.88

 pushes

0.85

 Pushing

0.84

Activations Density 0.160%

references to crashes or related failures in various contexts

No Comments

No Known Activations