INDEX

Explanations

instances where a condition is met or a potential consequence is mentioned

oai_token-act-pair · gpt-3.5-turbo

conditional phrases indicating potential situations or events

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

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

ļéĨĴ

-0.75

oked

-0.74

leground

-0.73

ãĤ¨ãĥ«

-0.71

nai

-0.70

zeb

-0.69

arse

-0.69

apsed

-0.68

alli

-0.68

resent

-0.68

POSITIVE LOGITS

 then

1.03

 chances

0.97

it

0.95

then

0.90

 surely

0.83

 however

0.83

 expect

0.83

 they

0.79

 hopefully

0.76

 perhaps

0.74

Activations Density 0.179%

instances where a condition is met or a potential consequence is mentioned

conditional phrases indicating potential situations or events

No Comments

No Known Activations