INDEX

Explanations

threats and references to danger or harm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

歓

-0.39

<eos>

-0.39

suy

-0.39

-0.38

spire

-0.38

 distanciation

-0.37

ׁ

-0.36

POSITIVE LOGITS

 myſelf

1.02

 itſelf

0.96

 threaten

0.96

 houſe

0.96

 Majefty

0.94

 threatened

0.94

ſelf

0.94

 juſt

0.94

 threatens

0.93

 ſever

0.92

Activations Density 0.282%

threats and references to danger or harm

No Comments

No Known Activations