INDEX

Explanations

references to scientific experiments

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "experiment."

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

othy

-0.70

headers

-0.67

doms

-0.66

CHAPTER

-0.65

nergy

-0.63

ACTED

-0.62

cut

-0.60

clinton

-0.60

vae

-0.59

miah

-0.59

POSITIVE LOGITS

imental

1.03

iments

0.99

iment

0.91

 experiment

0.91

 Experiment

0.89

ally

0.84

ually

0.79

eers

0.78

 experimenting

0.77

 experimented

0.74

Activations Density 0.016%

references to scientific experiments

occurrences of the word "experiment."

No Comments

No Known Activations