INDEX

Explanations

the word "along"

oai_token-act-pair · gpt-3.5-turbo

the phrase "go along" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĳå£«

-0.78

ĻĤ

-0.77

ilies

-0.68

ns

-0.68

orians

-0.67

Rated

-0.66

 helicop

-0.65

onomy

-0.63

orius

-0.62

ongyang

-0.62

POSITIVE LOGITS

ments

0.78

wagon

0.76

ities

0.73

side

0.71

leys

0.70

iously

0.65

 wagon

0.65

ity

0.65

stairs

0.65

erous

0.64

Activations Density 0.017%

the word "along"

the phrase "go along" and its variations

No Comments

No Known Activations