INDEX

Explanations

verbs denoting the beginning or initiation of an action

oai_token-act-pair · gpt-3.5-turbo

the infinitive form of verbs, particularly "to" followed by verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

enance

-0.71

cart

-0.69

soDeliveryDate

-0.66

afety

-0.63

 regards

-0.62

 conveyed

-0.62

hent

-0.60

lain

-0.60

rats

-0.59

tips

-0.59

POSITIVE LOGITS

 accumulate

0.90

 negotiate

0.90

 explore

0.89

 earn

0.87

 compensate

0.87

 climb

0.87

 fray

0.86

ggles

0.84

 imitate

0.83

 dismantle

0.81

Activations Density 0.053%

verbs denoting the beginning or initiation of an action

the infinitive form of verbs, particularly "to" followed by verbs

No Comments

No Known Activations