INDEX

Explanations

instances of the word "possible."

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of maximizing potential or efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mare

-1.02

oute

-0.82

wr

-0.82

ente

-0.80

wa

-0.79

lua

-0.77

irez

-0.76

worn

-0.75

roller

-0.74

wu

-0.74

POSITIVE LOGITS

iary

0.80

 introdu

0.79

 srfAttach

0.75

 practicable

0.75

 indicators

0.71

 indication

0.70

isSpecialOrderable

0.70

 distingu

0.68

 conclud

0.68

 Ø§ÙĦ

0.67

Activations Density 0.019%

instances of the word "possible."

phrases emphasizing the concept of maximizing potential or efficiency

No Comments

No Known Activations