INDEX

Explanations

years

oai_token-act-pair · gpt-3.5-turbo

references to specific years, particularly focusing on the 1970s

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 entirety

-0.73

tro

-0.72

opher

-0.72

hed

-0.71

cho

-0.67

Edge

-0.66

wer

-0.64

unders

-0.64

 trader

-0.63

pace

-0.63

POSITIVE LOGITS

 ILCS

0.93

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.89

å¹

0.81

0.80

0.79

0.76

ĸļ

0.76

 "$:/

0.75

çļ

0.73

Activations Density 0.018%

years

references to specific years, particularly focusing on the 1970s

No Comments

No Known Activations