INDEX

Explanations

negations and their implications in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

cination

-0.64

 persons

-0.56

Cordialement

-0.53

 Persons

-0.52

KommentareTeilen

-0.50

☉

-0.49

indeed

-0.48

issements

-0.48

persons

-0.48

 nạ

-0.48

POSITIVE LOGITS

’)

1.26

’.

1.25

’,

1.21

’).

1.20

’:

1.12

’;

1.08

’?

1.06

’”

1.06

.’

1.06

”),

1.05

Activations Density 0.087%

negations and their implications in discussions

No Comments

No Known Activations