INDEX

Explanations

phrases indicating conclusions or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Pring

-0.84

lipop

-0.74

Okey

-0.73

LON

-0.71

 Beep

-0.69

 Alton

-0.69

'>{

-0.67

pee

-0.65

Waiting

-0.65

ateral

-0.65

POSITIVE LOGITS

 propOrder

1.13

 thus

1.05

ly

1.04

thus

0.93

Hentet

0.90

 Thus

0.88

Thus

0.86

 autorytatywna

0.85

Hence

0.84

 Hence

0.83

Activations Density 0.129%

phrases indicating conclusions or results

No Comments

No Known Activations