INDEX

Explanations

occurrences related to events that happened at one point in time and their aftermath

oai_token-act-pair · gpt-3.5-turbo

the word "since" indicating time progression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Solution

-0.61

 Traps

-0.60

amina

-0.59

 guiName

-0.58

abus

-0.58

idi

-0.57

atron

-0.56

nic

-0.55

 Commodore

-0.55

 corridors

-0.55

POSITIVE LOGITS

rely

1.02

 gone

0.95

ĸļ

0.94

gone

0.93

 undergone

0.93

 become

0.87

 been

0.86

been

0.85

 disbanded

0.78

 surpassed

0.75

Activations Density 0.016%

occurrences related to events that happened at one point in time and their aftermath

the word "since" indicating time progression

No Comments

No Known Activations