INDEX

Explanations

the meaning of words in various languages

oai_token-act-pair · gpt-3.5-turbo

definitions or meanings of words and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Blair

-0.82

odynamics

-0.77

owsky

-0.76

udic

-0.76

arton

-0.73

assic

-0.70

vable

-0.69

ONSORED

-0.68

abre

-0.66

Guest

-0.65

POSITIVE LOGITS

 pronounced

0.96

 suffix

0.90

 Meaning

0.87

 pronunciation

0.83

 plural

0.82

 ç¥ŀ

0.80

Ð

0.77

 initials

0.77

 abbre

0.75

 Sina

0.75

Activations Density 0.158%

the meaning of words in various languages

definitions or meanings of words and phrases

No Comments

No Known Activations