INDEX

Explanations

verbs related to considering or evaluating something

oai_token-act-pair · gpt-3.5-turbo

terms related to evaluation and usage 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

 Notting

-0.69

 Patriarch

-0.64

Born

-0.62

soever

-0.60

anon

-0.59

 convol

-0.59

ved

-0.58

 Berm

-0.58

 Hitchcock

-0.57

 moreover

-0.57

POSITIVE LOGITS

 purposes

1.63

 sake

1.45

 reasons

1.06

ummies

1.00

 purpose

0.87

farious

0.79

okers

0.74

 enhancement

0.73

 clarification

0.73

ulkan

0.70

Activations Density 0.269%

verbs related to considering or evaluating something

terms related to evaluation and usage in various contexts

No Comments

No Known Activations