INDEX

Explanations

phrases starting with 'If it' and analyzing potential outcomes

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 ILCS

-0.65

©¶æ¥µ

-0.59

NetMessage

-0.59

GROUND

-0.58

SHARE

-0.57

iband

-0.56

 Levine

-0.56

igmatic

-0.55

catentry

-0.55

 Vent

-0.54

POSITIVE LOGITS

 weren

1.12

 happens

1.11

 succeeds

1.08

 survives

1.07

 lasts

1.05

 bothers

1.04

 fails

1.01

 persists

0.99

 occurs

0.99

 rains

0.98

Activations Density 0.096%

phrases starting with 'If it' and analyzing potential outcomes

No Comments

No Known Activations