INDEX

Explanations

negative descriptors and insults related to individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

TagMode

-0.55

-0.49

ánd

-0.47

ChildIndex

-0.42

דו

-0.42

iciens

-0.41

\|\

-0.40

isel

-0.38

 kend

-0.38

dataSet

-0.38

POSITIVE LOGITS

 crap

0.88

 للمعارف

0.87

StructEnd

0.86

ThroughAttribute

0.86

protoc

0.85

 ProtoMessage

0.84

 bullshit

0.83

 morons

0.82

发表于

0.82

 idiotic

0.81

Activations Density 0.454%

negative descriptors and insults related to individuals or groups

No Comments

No Known Activations