INDEX

Explanations

the word "actual" appearing in a text

oai_token-act-pair · gpt-3.5-turbo

the term "actual" 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 @ 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

wich

-0.77

 Beware

-0.69

fu

-0.68

bay

-0.62

zy

-0.62

Gate

-0.61

 ashore

-0.60

adish

-0.60

lust

-0.60

 beware

-0.59

POSITIVE LOGITS

idad

1.03

ity

1.01

isation

0.98

ITY

0.97

izations

0.97

izable

0.91

aneous

0.91

isations

0.89

itÃ©

0.88

ignment

0.88

Activations Density 0.025%

the word "actual" appearing in a text

the term "actual" in various contexts

No Comments

No Known Activations