INDEX

Explanations

dates or time-related phrases

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or conditions that suggest infrequency or rarity

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

 Cosponsors

-0.62

Kah

-0.61

FG

-0.60

 Wilkinson

-0.54

Hes

-0.53

 Grizzlies

-0.53

 meanwhile

-0.51

VG

-0.49

 Advertisement

-0.48

 Gibraltar

-0.48

POSITIVE LOGITS

natureconservancy

0.64

depending

0.56

 coincidence

0.54

Closure

0.50

parent

0.49

 begg

0.47

urgical

0.47

 sibling

0.46

jri

0.45

daq

0.45

Activations Density 1.865%

dates or time-related phrases

expressions of uncertainty or conditions that suggest infrequency or rarity

No Comments

No Known Activations