INDEX

Explanations

instances where the word "its" is used

oai_token-act-pair · gpt-3.5-turbo

the word "its" in various contexts

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

ľ

-0.72

·

-0.71

©¶æ

-0.70

µ

-0.69

awa

-0.68

 contrace

-0.63

 destro

-0.63

¥µ

-0.63

rul

-0.62

cknow

-0.62

POSITIVE LOGITS

gerald

0.99

ters

0.98

chens

0.91

matter

0.91

itute

0.84

terness

0.83

ariat

0.82

airs

0.79

itution

0.79

chers

0.79

Activations Density 0.031%

instances where the word "its" is used

the word "its" in various contexts

No Comments

No Known Activations