INDEX

Explanations

specific nouns related to objects and containers used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

nvidia

-0.51

strptime

-0.48

AxisAlignment

-0.47

deo

-0.46

ద్య

-0.46

grains

-0.45

esen

-0.44

bite

-0.44

izr

-0.44

endphp

-0.43

POSITIVE LOGITS

psack

1.14

 bucket

0.98

 buckets

0.96

RenderAtEndOf

0.96

 containers

0.92

bucket

0.90

 pail

0.88

 pots

0.88

 boxes

0.86

 container

0.84

Activations Density 0.439%

specific nouns related to objects and containers used in various contexts

No Comments

No Known Activations