INDEX

Explanations

instances of the word "return" followed by a location or a personal pronoun

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "return to" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anooga

-0.75

erning

-0.68

kered

-0.68

 precursor

-0.64

anners

-0.63

erity

-0.62

sel

-0.60

ussen

-0.59

unning

-0.59

okane

-0.59

POSITIVE LOGITS

 haunt

0.85

 blows

0.72

ãĤ¼

0.70

 Ashes

0.69

owship

0.68

 fray

0.68

 shore

0.67

å£

0.67

abama

0.67

ITED

0.66

Activations Density 0.078%

instances of the word "return" followed by a location or a personal pronoun

instances of the phrase "return to" in various contexts

No Comments

No Known Activations