INDEX

Explanations

programming error messages and status codes

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

cotta

-0.69

lotti

-0.65

 broche

-0.61

 multip

-0.58

íqu

-0.57

 المالية

-0.57

Annette

-0.56

ENTOS

-0.56

 Lineup

-0.55

Studi

-0.55

POSITIVE LOGITS

ⓧ

0.91

 lenker

0.81

 الحره

0.79

uxxxx

0.79

")->

0.76

Portale

0.70

 AspNetCore

0.70

 ModelExpression

0.69

 ویکی‌پدی

0.68

]),

0.68

Activations Density 0.149%

programming error messages and status codes

No Comments

No Known Activations