INDEX

Explanations

past tense verbs

oai_token-act-pair · gpt-3.5-turbo

the word "was" and its variants indicating past actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seym

-0.71

arta

-0.66

stood

-0.62

 buckets

-0.57

holders

-0.56

 quotas

-0.53

 spheres

-0.53

BJ

-0.52

 marker

-0.52

 Grail

-0.52

POSITIVE LOGITS

wolves

0.99

wolf

0.95

hes

0.82

actionDate

0.75

ps

0.72

osponsors

0.72

0.68

 Flavoring

0.64

 released

0.64

othing

0.63

Activations Density 0.072%

past tense verbs

the word "was" and its variants indicating past actions or states

No Comments

No Known Activations