INDEX

Explanations

sections of code or programming constructs that include comments or markup tags

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

and

-0.54

-0.53

<eos>

-0.50

ken

-0.50

↵

-0.50

-0.49

 Waray

-0.49

-0.48

POSITIVE LOGITS

LookAnd

0.96

ngdoc

0.96

:✨

0.96

+#+

0.95

 &___

0.87

 Савезне

0.87

Hochspringen

0.87

 transférez

0.87

 Numerade

0.83

 distanciation

0.82

Activations Density 0.195%

sections of code or programming constructs that include comments or markup tags

No Comments

No Known Activations