INDEX

Explanations

expressions of apology and expressions of humility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 CreateTagHelper

-0.55

complexContent

-0.55

DebuggerNonUser

-0.55

 TextInputType

-0.55

CppMethod

-0.53

ModelAdmin

-0.52

ValueStyle

-0.52

RectangleBorder

-0.52

StoryboardSegue

-0.52

Dimanche

-0.51

POSITIVE LOGITS

 reciproc

0.45

 loyalty

0.41

reci

0.40

 reciprocity

0.38

 loyal

0.36

 recipro

0.34

 generosity

0.33

 kindness

0.33

 envers

0.32

 love

0.31

Activations Density 0.247%

expressions of apology and expressions of humility

No Comments

No Known Activations