INDEX

Explanations

words related to forgiveness and acceptance

oai_token-act-pair · gpt-3.5-turbo

variations of the word "great"

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

eers

-0.73

phrine

-0.62

 shortened

-0.62

 burg

-0.61

 sexes

-0.61

mortem

-0.61

 vitro

-0.60

doors

-0.60

 messenger

-0.60

WER

-0.60

POSITIVE LOGITS

illing

1.02

iffin

1.00

ille

1.00

ains

0.98

asp

0.98

rl

0.96

anting

0.96

iddle

0.94

gr

0.94

illed

0.94

Activations Density 0.004%

words related to forgiveness and acceptance

variations of the word "great"

No Comments

No Known Activations