INDEX

Explanations

phrases related to legislation and legal actions

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating location or context

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

mons

-0.61

auga

-0.61

uch

-0.61

yre

-0.60

irin

-0.60

joice

-0.60

uts

-0.60

layer

-0.59

agog

-0.58

ynes

-0.58

POSITIVE LOGITS

 itself

0.84

 himself

0.80

 ourselves

0.78

 themselves

0.72

 myself

0.70

 herself

0.70

 aloud

0.67

 oneself

0.67

quickShipAvailable

0.64

 Marino

0.63

Activations Density 0.498%

phrases related to legislation and legal actions

prepositions and phrases indicating location or context

No Comments

No Known Activations