INDEX

Explanations

sequences of numbers and symbols in a specific order

oai_token-act-pair · gpt-3.5-turbo

sequences of numerical values, particularly those that indicate lists or increments

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

 Gathering

-0.64

uggest

-0.64

Executive

-0.61

 estimating

-0.60

 sponsoring

-0.59

bda

-0.58

 manufacturing

-0.57

assis

-0.56

 palpable

-0.56

creat

-0.54

POSITIVE LOGITS

etc

0.99

etc

0.97

ĪĴ

0.78

 respectively

0.73

illance

0.70

opt

0.68

âĢ¦)

0.65

 parentheses

0.65

...)

0.65

Shift

0.63

Activations Density 0.136%

sequences of numbers and symbols in a specific order

sequences of numerical values, particularly those that indicate lists or increments

No Comments

No Known Activations