INDEX

Explanations

quantities or amounts of things mentioned in the texts

oai_token-act-pair · gpt-3.5-turbo

phrases that quantify or refer to measurements or amounts

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

ĸļ

-1.10

\\\\\\\\

-0.88

edin

-0.81

ħĭ

-0.81

ÙĲ

-0.81

reys

-0.78

stocks

-0.75

Õ

-0.74

\'

-0.73

Ń·

-0.73

POSITIVE LOGITS

 allowable

0.92

 accumulated

0.91

 money

0.88

 mileage

0.86

 overlap

0.85

 fines

0.84

 energy

0.83

 ingested

0.80

 absorbed

0.78

 effort

0.78

Activations Density 0.047%

quantities or amounts of things mentioned in the texts

phrases that quantify or refer to measurements or amounts

No Comments

No Known Activations