INDEX

Explanations

the term "vs" or its variations used in comparisons or contrasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Electra

-0.66

 Heid

-0.61

ungkinkan

-0.59

eer

-0.58

ranean

-0.58

NAL

-0.58

터

-0.56

fap

-0.56

 LAMP

-0.56

fiore

-0.55

POSITIVE LOGITS

vs

2.59

 versus

2.27

 Versus

2.04

Vs

2.02

versus

1.85

vs

1.81

Versus

1.73

VS

1.72

 Against

1.40

Against

1.40

Activations Density 0.066%

the term "vs" or its variations used in comparisons or contrasts

No Comments

No Known Activations