INDEX

Explanations

phrases indicating uncertainty or possibility

oai_token-act-pair · gpt-3.5-turbo

the word "perhaps" and its variations, indicating uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

chens

-0.73

nen

-0.73

emy

-0.72

arthed

-0.71

zeb

-0.71

ombat

-0.71

zen

-0.70

ulative

-0.69

jriwal

-0.69

elight

-0.69

POSITIVE LOGITS

 unsurprisingly

0.84

haps

0.80

 opio

0.77

 someday

0.76

 sensing

0.73

 "$:/

0.71

 unemploy

0.68

 involuntary

0.67

 tempted

0.66

 infer

0.65

Activations Density 0.025%

phrases indicating uncertainty or possibility

the word "perhaps" and its variations, indicating uncertainty or speculation

No Comments

No Known Activations