INDEX

Explanations

formatted section comments and documentation in coding contexts

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

sizeCache

-1.08

IsMutable

-0.88

 ProtoMessage

-0.77

 ModelExpression

-0.75

IsContent

-0.69

OfDay

-0.68

 Meksiku

-0.66

 архивлан

-0.65

WriteBarrier

-0.64

وأضاف

-0.63

POSITIVE LOGITS

****************

1.66

################

0.83

================

0.78

----------------

0.76

________________

0.76

**************

0.66

————————————————

0.66

~~~~~~~~~~~~~~~~

0.65

***************

0.64

0.62

Activations Density 0.152%

formatted section comments and documentation in coding contexts

No Comments

No Known Activations