INDEX

Explanations

references to quantities or measurements related to food or drink

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 position

-0.49

ar

-0.49

all

-0.48

 multiple

-0.47

</i>

-0.45

</b>

-0.45

后退

-0.44

har

-0.43

isch

-0.43

POSITIVE LOGITS

AddTagHelper

1.03

TemporalType

1.00

InjectAttribute

0.89

 AssemblyCompany

0.87

ISupport

0.86

ContentAsync

0.86

ScopeManager

0.86

AddWithValue

0.86

 defaultstate

0.85

 FetchType

0.84

Activations Density 0.221%

references to quantities or measurements related to food or drink

No Comments

No Known Activations