INDEX

Explanations

phrases related to automatic actions or processes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "automatically."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Straw

-0.82

 Tate

-0.75

ĸļ

-0.74

wife

-0.72

 Emin

-0.72

ergus

-0.69

 Kerry

-0.68

 Sherman

-0.67

rug

-0.67

 Mouth

-0.67

POSITIVE LOGITS

 populate

0.97

 detects

0.91

 automatically

0.90

 migrate

0.90

 induct

0.89

untarily

0.88

 deducted

0.86

 regenerate

0.86

 assume

0.85

 detect

0.85

Activations Density 0.010%

phrases related to automatic actions or processes

instances of the word "automatically."

No Comments

No Known Activations