INDEX

Explanations

the word "and."

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" used frequently throughout the text

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

Deal

-0.86

oldemort

-0.79

Report

-0.76

Recomm

-0.76

:[

-0.74

inational

-0.70

)[

-0.69

interrupted

-0.69

account

-0.69

POSITIVE LOGITS

rogens

1.02

rogen

0.92

 Sons

0.91

romeda

0.83

ERSON

0.75

 Associates

0.73

 therefore

0.70

rew

0.68

ryn

0.65

 Beyond

0.64

Activations Density 0.357%

the word "and."

the conjunction "and" used frequently throughout the text

No Comments

No Known Activations