INDEX

Explanations

conditional phrases expressing desires or recommendations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Ennis

-0.89

 Adair

-0.80

 swans

-0.77

 Lipa

-0.74

 Freitas

-0.73

 Schwan

-0.71

 noun

-0.71

cephala

-0.70

 Reina

-0.70

 Ciro

-0.70

POSITIVE LOGITS

 would

1.96

 Would

1.82

 WOULD

1.78

Would

1.76

would

1.70

ULD

1.17

 could

1.12

ould

1.10

 wouldn

1.04

 würde

1.04

Activations Density 0.237%

conditional phrases expressing desires or recommendations

No Comments

No Known Activations

conditional phrases expressing desires or recommendations

No Comments

No Known Activations