INDEX

Explanations

colons followed by sentences

oai_token-act-pair · gpt-3.5-turbo

punctuation or formatting indicators in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 reconc

-0.74

 tremend

-0.73

æ©

-0.72

 ingred

-0.70

 territ

-0.68

 bean

-0.66

¥ŀ

-0.65

 adversaries

-0.65

 diseng

-0.65

 manif

-0.64

POSITIVE LOGITS

 âĨĳ

1.35

 Originally

1.10

Originally

0.91

Show

0.88

 Interesting

0.88

 Regarding

0.85

 Yeah

0.84

 Assuming

0.84

 Whilst

0.82

>>

0.81

Activations Density 0.059%

colons followed by sentences

punctuation or formatting indicators in the text

No Comments

No Known Activations