INDEX

Explanations

terms related to the natural world or the prefix "natur"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "nature" and related terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 edible

-0.67

Sil

-0.62

bone

-0.62

 Ashton

-0.61

 awoken

-0.59

ortium

-0.57

isSpecialOrderable

-0.57

 stub

-0.57

ĪĴ

-0.56

esses

-0.56

POSITIVE LOGITS

ificent

0.99

als

0.94

aling

0.92

itas

0.88

tarian

0.87

ating

0.85

itÃ©

0.84

ated

0.84

adian

0.84

aton

0.84

Activations Density 0.042%

terms related to the natural world or the prefix "natur"

variations of the word "nature" and related terms

No Comments

No Known Activations