INDEX

Explanations

references to academic articles or publications

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

)->

-0.65

<()>

-0.61

</strong>

-0.60

 Stein

-0.59

 Stolz

-0.59

Pisces

-0.57

 فريبيس

-0.57

 Pell

-0.57

 Meksiku

-0.56

 eset

-0.56

POSITIVE LOGITS

Rev

2.38

Rev

2.31

REV

2.11

rev

2.10

rev

1.93

REV

1.90

PhysRev

1.55

 Revolution

1.46

 revs

1.46

 revolutions

1.41

Activations Density 0.067%

references to academic articles or publications

No Comments

No Known Activations