INDEX

Explanations

the word "maybe" in various contexts

oai_token-act-pair · gpt-3.5-turbo

the word "maybe" and other expressions of uncertainty or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lete

-0.88

ocaust

-0.85

cies

-0.85

ife

-0.85

iak

-0.83

ombat

-0.82

iya

-0.77

ament

-0.77

ken

-0.75

arthed

-0.75

POSITIVE LOGITS

 someday

1.13

 subconscious

0.77

haps

0.73

 SOME

0.69

 unsurprisingly

0.68

 sensing

0.67

 opio

0.67

 even

0.66

 unintentionally

0.66

 accidentally

0.64

Activations Density 0.036%

the word "maybe" in various contexts

the word "maybe" and other expressions of uncertainty or possibility

No Comments

No Known Activations