INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific character names or initials

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

 wide

-0.83

ãĤ°

-0.64

 Wide

-0.64

assetsadobe

-0.61

 commons

-0.60

 slideshow

-0.59

 lawn

-0.59

ãĥ£

-0.59

 ______

-0.58

CMS

-0.58

POSITIVE LOGITS

usk

0.93

utter

0.92

err

0.92

aren

0.89

essel

0.87

abi

0.87

ohan

0.84

amm

0.84

adish

0.83

oka

0.83

Activations Density 0.193%

proper nouns

occurrences of specific character names or initials

No Comments

No Known Activations