INDEX

Explanations

questions being asked to someone

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Asked" indicating a question or inquiry within the text

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

audi

-0.72

marine

-0.72

psc

-0.71

;;;;;;;;;;;;

-0.69

cutting

-0.69

lim

-0.68

rio

-0.66

EStreamFrame

-0.66

equal

-0.66

photos

-0.66

POSITIVE LOGITS

 questions

1.14

 Questions

1.08

 rhet

1.07

 asked

1.05

 Asked

0.94

 asks

0.91

 questioned

0.91

 quizz

0.89

 probing

0.88

ioned

0.88

Activations Density 0.018%

questions being asked to someone

instances of the word "Asked" indicating a question or inquiry within the text

No Comments

No Known Activations