INDEX

Explanations

phrases related to conflict, aggression, violence, and intense situations

oai_token-act-pair · gpt-3.5-turbo

intense and dramatic expressions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Brow

-0.55

 policymakers

-0.54

ESA

-0.54

 Corbyn

-0.50

 HuffPost

-0.50

 ÂŃ

-0.50

 Investigative

-0.49

 Observer

-0.49

ÂŃ

-0.48

 assessments

-0.48

POSITIVE LOGITS

..."

0.84

 ..."

0.82

...)

0.77

 fuckin

0.76

 hemor

0.71

 blah

0.70

-"

0.68

;)

0.68

tho

0.67

âĢ¦)

0.67

Activations Density 2.963%

phrases related to conflict, aggression, violence, and intense situations

intense and dramatic expressions or events

No Comments

No Known Activations