INDEX

Explanations

expressions of strong negative emotions or insults

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 established

-0.44

ForRow

-0.44

wnież

-0.41

:_

-0.41

oa̍t

-0.40

twimg

-0.39

Personensuche

-0.39

Established

-0.38

 ModelExpression

-0.38

 للاسماء

-0.38

POSITIVE LOGITS

 stupid

1.34

 idiot

1.24

 idiots

1.22

 idiotic

1.22

stupid

1.19

 lousy

1.17

 morons

1.12

 bastards

1.09

 crap

1.09

 disgusting

1.08

Activations Density 0.363%

expressions of strong negative emotions or insults

No Comments

No Known Activations