INDEX

Explanations

references to bans and regulations

oai_token-act-pair · gpt-3.5-turbo

references to prohibitions or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Generations

-0.73

 IMAGES

-0.70

 Zeit

-0.64

lycer

-0.64

 Apostles

-0.64

rious

-0.62

 Rhythm

-0.61

 PROG

-0.60

 Temper

-0.59

 rendition

-0.59

POSITIVE LOGITS

ishment

1.22

hammer

1.08

hee

1.00

tering

0.96

ishing

0.94

zai

0.92

nered

0.88

jo

0.84

eful

0.84

ish

0.82

Activations Density 0.035%

references to bans and regulations

references to prohibitions or restrictions

No Comments

No Known Activations