INDEX

Explanations

instances of the word "posting" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

RICULUM

-0.57

vábbi

-0.54

EMON

-0.53

lerc

-0.52

NOSTIC

-0.49

ocide

-0.49

mor

-0.48

⁩

-0.48

limite

-0.47

uremberg

-0.46

POSITIVE LOGITS

 posting

1.32

Posted

1.17

Posting

1.14

 postings

1.11

 Posted

1.08

 Posting

1.06

posting

1.01

posted

0.98

 posted

0.96

 posts

0.93

Activations Density 0.064%

instances of the word "posting" or variations of it

No Comments

No Known Activations