INDEX

Explanations

statements related to editorials or opinion pieces

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "op-ed" and variations thereof

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

owship

-0.81

enance

-0.73

ashtra

-0.63

 Roses

-0.60

beit

-0.57

cliffe

-0.57

UAL

-0.57

worthiness

-0.56

 untold

-0.56

 Dane

-0.55

POSITIVE LOGITS

monary

0.78

sylvania

0.78

Doc

0.75

lisher

0.75

gres

0.68

reme

0.67

heid

0.67

ela

0.66

ansion

0.65

matic

0.64

Activations Density 0.071%

statements related to editorials or opinion pieces

occurrences of the term "op-ed" and variations thereof

No Comments

No Known Activations