INDEX

Explanations

technical or complex terms related to controversial or problematic issues

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating a lack of clarity or controversy

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

uyomi

-0.71

hyde

-0.68

anwhile

-0.68

 coefficients

-0.67

 Values

-0.66

 immersion

-0.65

ä»£

-0.64

 bands

-0.63

anism

-0.62

 Dwell

-0.61

POSITIVE LOGITS

structed

1.06

hibited

1.00

ported

0.99

leased

0.97

aturally

0.96

ceivable

0.96

assuming

0.95

vised

0.94

ufact

0.91

achable

0.90

Activations Density 0.037%

technical or complex terms related to controversial or problematic issues

words and phrases indicating a lack of clarity or controversy

No Comments

No Known Activations