INDEX

Explanations

conjunctions and words related to health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 domicilio

-0.56

 laikā

-0.51

ulement

-0.47

masta

-0.46

 esteja

-0.46

 hemma

-0.46

cerna

-0.45

áneos

-0.45

 découver

-0.44

のうち

-0.44

POSITIVE LOGITS

ThroughAttribute

0.68

ArgsConstructor

0.66

WriteLiteral

0.66

etc

0.64

Etc

0.63

WriteTagHelper

0.63

ContentLoaded

0.63

#+#

0.63

ükü

0.60

principalColumn

0.60

Activations Density 0.247%

conjunctions and words related to health

No Comments

No Known Activations