INDEX

Explanations

references to gore and bodily harm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 BoxDecoration

-0.60

 שוליים

-0.57

InjectAttribute

-0.53

 Superhosts

-0.52

GeneratedMessage

-0.50

DatabaseError

-0.50

Бахар

-0.49

 surla

-0.49

zeptember

-0.49

ArrowToggle

-0.49

POSITIVE LOGITS

 corpses

1.06

 corpse

1.06

 decomposed

0.96

 mutilated

0.93

 decom

0.92

 carcasses

0.91

 dissected

0.91

 carcass

0.89

 headless

0.88

 rotting

0.87

Activations Density 0.436%

references to gore and bodily harm

No Comments

No Known Activations