INDEX

Explanations

specific time zone abbreviations such as 'PDT' and 'PST'

oai_token-act-pair · gpt-3.5-turbo

time zone abbreviations

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

amac

-0.75

hist

-0.70

venge

-0.70

actor

-0.69

proof

-0.66

gotten

-0.65

neys

-0.64

stay

-0.64

 welfare

-0.64

pir

-0.63

POSITIVE LOGITS

EDT

1.05

CET

0.94

DAQ

0.89

PDT

0.86

EST

0.79

EMBER

0.79

CST

0.77

GMT

0.76

KO

0.75

+/-

0.74

Activations Density 0.022%

specific time zone abbreviations such as 'PDT' and 'PST'

time zone abbreviations

No Comments

No Known Activations