INDEX

Explanations

phrases related to war crimes

oai_token-act-pair · gpt-3.5-turbo

references to war crimes and human rights violations

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

BIT

-0.79

ŃĶ

-0.78

ãĤ¨ãĥ«

-0.73

ãĥ¥

-0.73

rez

-0.70

upper

-0.70

ivas

-0.69

onom

-0.68

ãĥĥ

-0.68

Nav

-0.68

POSITIVE LOGITS

 bikini

0.69

ioxide

0.69

 imitation

0.67

 analogy

0.62

 Tuls

0.60

 extraord

0.60

 pamph

0.59

TED

0.58

 billionaires

0.58

 equivalents

0.58

Activations Density 0.320%

phrases related to war crimes

references to war crimes and human rights violations

No Comments

No Known Activations