INDEX

Explanations

intensifiers that emphasize the degree or quality of a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

writeFieldEnd

-0.79

 Foil

-0.61

PSD

-0.56

 onLoad

-0.55

 cauſe

-0.55

Opal

-0.53

 displacement

-0.52

 Litchfield

-0.52

 Opal

-0.52

HCM

-0.52

POSITIVE LOGITS

 very

0.95

 Very

0.93

very

0.90

Very

0.88

 VERY

0.85

VERY

0.76

Molto

0.73

Muy

0.71

Muy

0.69

очень

0.69

Activations Density 0.118%

intensifiers that emphasize the degree or quality of a subject

No Comments

No Known Activations