INDEX

Explanations

time periods

oai_token-act-pair · gpt-3.5-turbo

references to specific time periods

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

ply

-0.82

dain

-0.71

found

-0.70

tty

-0.67

XY

-0.67

birds

-0.67

ÄŁ

-0.66

 Cosponsors

-0.65

RAY

-0.65

Always

-0.64

POSITIVE LOGITS

 periods

1.17

icals

1.09

ional

1.00

period

0.86

 period

0.86

ical

0.83

icity

0.82

ftime

0.80

oths

0.75

 Period

0.75

Activations Density 0.026%

time periods

references to specific time periods

No Comments

No Known Activations