INDEX

Explanations

specific programming or markup language elements

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

cshtml

-1.22

SourceChecksum

-1.12

SequentialGroup

-1.12

tagHelperRunner

-1.10

ViewFeatures

-1.04

Билгалдахарш

-1.02

ScopeManager

-0.98

ɵɵ

-0.98

 jScrollPane

-0.98

ArgsConstructor

-0.96

POSITIVE LOGITS

<bos>

0.47

новниш

0.41

țul

0.38

 referred

0.38

preds

0.37

URLEncoder

0.37

Attributed

0.36

Ciri

0.35

 submission

0.35

0.34

Activations Density 0.012%

specific programming or markup language elements

No Comments

No Known Activations