INDEX

Explanations

number-related strings

oai_token-act-pair · gpt-3.5-turbo

data related to percentages and statistical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

pedia

-0.64

pecially

-0.63

cul

-0.58

EStream

-0.58

ometime

-0.58

 itiner

-0.58

etheus

-0.57

 inconsist

-0.57

cules

-0.57

jamin

-0.57

POSITIVE LOGITS

lycer

0.86

GDP

0.82

 rate

0.80

 Rate

0.75

elsen

0.73

 variance

0.72

ococ

0.71

elsius

0.71

ved

0.71

(%

0.70

Activations Density 0.233%

number-related strings

data related to percentages and statistical values

No Comments

No Known Activations