INDEX

Explanations

phrases indicating possibility or prediction

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "to be" and their grammatical variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ãĥ¼ãĥ«

-0.87

ulously

-0.84

shall

-0.76

ĸļ

-0.74

ãĤ¼ãĤ¦ãĤ¹

-0.68

anwhile

-0.66

lance

-0.65

 doubtless

-0.65

rones

-0.65

)))

-0.64

POSITIVE LOGITS

 tempted

1.05

 able

0.97

 underest

0.89

 forgiven

0.88

 overest

0.86

 swayed

0.84

 construed

0.84

 lurking

0.82

 preferable

0.81

 mistaken

0.81

Activations Density 0.119%

phrases indicating possibility or prediction

forms of the verb "to be" and their grammatical variations

No Comments

No Known Activations