INDEX

Explanations

official names or titles, likely in the context of authors or creators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

reactstrap

-0.62

parsedMessage

-0.61

zyści

-0.54

entrion

-0.54

orino

-0.53

+][

-0.53

ECONDS

-0.51

SharedCtor

-0.51

unknownFields

-0.50

SharedDtor

-0.50

POSITIVE LOGITS

 itſelf

0.54

üyada

0.53

RatingBar

0.51

 impra

0.50

 Rima

0.49

 myſelf

0.49

 Spart

0.49

Efq

0.49

ponen

0.48

 Dessa

0.47

Activations Density 0.060%

official names or titles, likely in the context of authors or creators

No Comments

No Known Activations