INDEX

Explanations

words or phrases that indicate a sense of something strange or bizarre

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 onCancelled

-0.85

 anjo

-0.63

 ejus

-0.61

 fallait

-0.58

 dreamstime

-0.57

 pouvoit

-0.56

 nød

-0.56

 montée

-0.56

 jaunes

-0.55

 senador

-0.55

POSITIVE LOGITS

ish

1.34

ISH

1.14

ishes

0.94

ishness

0.83

ishable

0.82

ish

0.81

isha

0.76

ISHING

0.73

 дописавши

0.73

ishing

0.71

Activations Density 0.054%

words or phrases that indicate a sense of something strange or bizarre

No Comments

No Known Activations