INDEX

Explanations

connections and mechanisms related to scientific explanations and hypotheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 itſelf

-1.51

 myſelf

-1.51

 pleaſure

-1.39

Efq

-1.38

 Jefus

-1.31

 purpoſe

-1.31

 himſelf

-1.30

 ſmall

-1.26

 Majefty

-1.24

 houſe

-1.24

POSITIVE LOGITS

 mechanism

0.62

Ma

0.61

van

0.58

for

0.58

za

0.57

Ho

0.56

 hypothesized

0.54

tu

0.54

Activations Density 2.690%

connections and mechanisms related to scientific explanations and hypotheses

No Comments

No Known Activations

connections and mechanisms related to scientific explanations and hypotheses

No Comments

No Known Activations