INDEX

Explanations

the usage of the word "a" followed by a noun

oai_token-act-pair · gpt-3.5-turbo

instances of the article "a"

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

Edit

-0.81

fn

-0.77

achu

-0.76

attacks

-0.73

alion

-0.72

Attempts

-0.71

edit

-0.69

Changes

-0.69

Element

-0.68

flows

-0.67

POSITIVE LOGITS

 lifelong

0.95

bit

0.92

 proud

0.90

 busy

0.89

 terrific

0.88

verse

0.87

 decent

0.87

lot

0.85

 healthy

0.84

 reliable

0.82

Activations Density 0.322%

the usage of the word "a" followed by a noun

instances of the article "a"

No Comments

No Known Activations