INDEX

Explanations

language related to actions, decisions, and interactions, particularly in contexts of conflict or resolution

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

writeFieldEnd

-0.86

ArgsConstructor

-0.78

AutoScaleMode

-0.74

bleau

-0.66

 doubtnut

-0.64

 bezeichneter

-0.64

bagai

-0.64

AddTagHelper

-0.63

AddHtmlAttribute

-0.62

 XNUMX

-0.62

POSITIVE LOGITS

us

3.06

me

3.03

him

2.59

 them

2.58

them

1.86

you

1.62

him

1.56

 THEM

1.55

me

1.47

eux

1.46

Activations Density 2.279%

language related to actions, decisions, and interactions, particularly in contexts of conflict or resolution

No Comments

No Known Activations