INDEX

Explanations

references to political figures and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.53

 صوتيه

-0.42

WebElementEntity

-0.41

nsyn

-0.41

jspx

-0.40

 ***!

-0.39

SourceChecksum

-0.39

eqn

-0.38

UnusedPrivate

-0.37

UserScript

-0.37

POSITIVE LOGITS

sterious

0.59

 étrange

0.55

 suspiciously

0.54

 misterioso

0.52

 extraño

0.50

 misteriosa

0.49

 mysterious

0.49

 soudain

0.48

Strange

0.48

 suspicious

0.48

Activations Density 0.156%

references to political figures and their actions

No Comments

No Known Activations