INDEX

Explanations

the word "substantial" and related words

oai_token-act-pair · gpt-3.5-turbo

the word "substantial."

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

yer

-0.71

sell

-0.68

tein

-0.66

say

-0.66

 Commissioners

-0.66

cius

-0.65

elf

-0.64

 Station

-0.64

rology

-0.64

alias

-0.63

POSITIVE LOGITS

 amounts

1.10

 quantities

1.06

 portions

0.93

 amount

0.90

 enough

0.87

 earthqu

0.82

stantial

0.81

 chunk

0.80

enough

0.79

 sized

0.78

Activations Density 0.006%

the word "substantial" and related words

the word "substantial."

No Comments

No Known Activations