INDEX

Explanations

expressions of uncertainty or inability to perform an action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

__':

-0.64

__":

-0.59

معلومات

-0.57

makeText

-0.54

 gainera

-0.53

NameInMap

-0.53

 resourceCulture

-0.53

OrNil

-0.52

 发表于

-0.52

 gezien

-0.52

POSITIVE LOGITS

 find

3.07

find

2.69

 finds

2.55

 Find

2.36

 finding

2.34

Find

2.31

 FIND

2.25

finds

2.09

FIND

2.09

finding

2.05

Activations Density 0.684%

expressions of uncertainty or inability to perform an action

No Comments

No Known Activations