INDEX

Explanations

instances where something is being added or included

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "addition."

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

Negative Logits

bis

-0.73

bane

-0.65

ARDS

-0.65

 Prediction

-0.64

generic

-0.60

meta

-0.60

ESE

-0.59

 Neutral

-0.59

rics

-0.58

ollo

-0.58

POSITIVE LOGITS

xual

0.88

ition

0.83

itious

0.82

 thereto

0.79

endum

0.74

tions

0.70

ract

0.70

 bonus

0.70

itive

0.69

itionally

0.68

Activations Density 0.015%

instances where something is being added or included

occurrences of the word "addition."

No Known Activations