INDEX

Explanations

document structure indicators or formatting tags

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

-0.52

jsonwebtoken

-0.46

 will

-0.46

-0.43

-0.41

she

-0.39

 nime

-0.39

as

-0.39

TabIndex

-0.38

POSITIVE LOGITS

 pinulongan

0.90

 يتيمه

0.85

jsxFileName

0.84

IndentedString

0.79

̈́

0.76

 Signalez

0.75

はじめに

0.75

 Majefty

0.75

########.

0.73

enderror

0.73

Activations Density 0.081%

document structure indicators or formatting tags

No Comments

No Known Activations