INDEX

Explanations

numerical values such as prices, interest rates, costs, and levels

oai_token-act-pair · gpt-3.5-turbo

differentials and comparisons related to scale, cost, and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

andals

-0.70

STEM

-0.69

ules

-0.66

 Tayyip

-0.63

ullah

-0.62

 Malays

-0.62

ister

-0.60

 Chronicles

-0.59

letters

-0.59

thia

-0.59

POSITIVE LOGITS

 behest

1.17

 expense

1.03

 disadvantage

0.89

 discretion

0.86

 level

0.85

 outset

0.85

 mercy

0.83

 apiece

0.82

 disposal

0.82

 intervals

0.82

Activations Density 0.395%

numerical values such as prices, interest rates, costs, and levels

differentials and comparisons related to scale, cost, and performance metrics

No Comments

No Known Activations