INDEX

Explanations

instances of significant changes or effects in research results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ModelExpression

-0.60

дешь

-0.57

soort

-0.55

valdo

-0.55

🇴

-0.54

örté

-0.53

 مُعرِّف

-0.53

esh

-0.53

показания

-0.53

איך

-0.52

POSITIVE LOGITS

 significantly

3.54

significantly

3.07

 substantially

2.85

 considerably

2.74

 Significantly

2.59

 drastically

2.54

 greatly

2.50

 dramatically

2.40

 markedly

2.39

 appreciably

2.21

Activations Density 0.100%

instances of significant changes or effects in research results

No Comments

No Known Activations