INDEX

Explanations

specific demonstrative pronouns indicating objects or subjects in a discussion

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

الدراسه

-0.74

zzleHttp

-0.73

ロウィン

-0.71

fromnode

-0.64

pecabe

-0.64

majánló

-0.64

Obrázky

-0.62

iſten

-0.62

ɵɵelement

-0.61

OGND

-0.61

POSITIVE LOGITS

0.52

0.42

This

0.40

0.39

↵↵

0.38

We

0.38

my

0.37

[^

0.36

Activations Density 0.068%

specific demonstrative pronouns indicating objects or subjects in a discussion

No Comments

No Known Activations