INDEX

Explanations

references to specific instances, examples, or notable phrases within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

StoryboardSegue

-0.64

 communs

-0.62

ंदीखरीदारी

-0.61

 مشين

-0.61

tagHelperRunner

-0.60

 zvuky

-0.59

 normaux

-0.59

 vacanze

-0.59

 referenties

-0.59

 dingen

-0.59

POSITIVE LOGITS

 particular

1.31

 same

1.08

 latter

0.96

 very

0.94

particular

0.91

 specific

0.86

 regard

0.85

 most

0.81

 respective

0.80

 latest

0.80

Activations Density 0.386%

references to specific instances, examples, or notable phrases within the text

No Comments

No Known Activations