INDEX

Explanations

dates in the format 'YYYY' that relate to significant events or periods of time

oai_token-act-pair · gpt-3.5-turbo

references to the year 2016

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

iple

-0.69

imen

-0.67

phia

-0.65

 precaution

-0.65

 snipp

-0.64

angs

-0.63

 cumbers

-0.62

 prick

-0.62

bip

-0.61

 clipping

-0.61

POSITIVE LOGITS

1.06

å¹

0.86

bleacher

0.79

peak

0.73

nd

0.72

 Became

0.72

âĢ²

0.71

âĢ³

0.70

ileaks

0.68

Activations Density 0.041%

dates in the format 'YYYY' that relate to significant events or periods of time

references to the year 2016

No Comments

No Known Activations