INDEX

Explanations

references to specific individuals and their relationships or actions

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

ίναι

-0.44

 Cost

-0.42

ëren

-0.41

 klubben

-0.40

px

-0.40

kozá

-0.39

 ritratto

-0.39

ridge

-0.39

rige

-0.39

 costes

-0.39

POSITIVE LOGITS

InjectAttribute

1.02

UnusedPrivate

0.93

 wireType

0.91

TagMode

0.88

InvalidProtocol

0.87

Personendaten

0.87

sizeCache

0.86

webElement

0.82

setVerticalGroup

0.81

RenderAtEndOf

0.80

Activations Density 0.664%

references to specific individuals and their relationships or actions

No Comments

No Known Activations