INDEX

Explanations

discussion about choices and decision-making

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

Rohy

-0.57

 avulla

-0.55

AddTagHelper

-0.54

final

-0.53

 homicidio

-0.53

PostMapping

-0.51

bono

-0.50

 vode

-0.49

xil

-0.48

 chi̍t

-0.48

POSITIVE LOGITS

 choices

1.24

 hormone

1.19

 hormones

1.01

 Hormone

1.01

 Choices

0.98

horm

0.95

Horm

0.92

脚注の使い方

0.89

 decisions

0.82

 virtue

0.82

Activations Density 0.172%

discussion about choices and decision-making

No Comments

No Known Activations