INDEX

Explanations

information related to events like accidents, incidents, arrests, and reports

oai_token-act-pair · gpt-3.5-turbo

comma-separated phrases or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

sylv

-0.70

 Millenn

-0.65

 FOIA

-0.65

 awhile

-0.65

NetMessage

-0.64

 instructional

-0.63

!--

-0.62

:(

-0.61

 realization

-0.60

ggles

-0.59

POSITIVE LOGITS

 organisers

0.99

 whilst

0.95

 although

0.92

 albeit

0.92

 namely

0.90

 according

0.90

 Fifa

0.89

 Notting

0.89

 Defence

0.87

Scotland

0.85

Activations Density 0.733%

information related to events like accidents, incidents, arrests, and reports

comma-separated phrases or lists

No Comments

No Known Activations