INDEX

Explanations

proper nouns or specific product names

oai_token-act-pair · gpt-3.5-turbo

the word "Ins" that likely indicates a specific topic or section in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

AUT

-0.82

ĸļ

-0.77

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.76

âĢ¢âĢ¢

-0.70

lda

-0.69

 Mata

-0.69

>>>>>>>>

-0.68

dylib

-0.67

çĦ

-0.67

¶ħ

-0.66

POSITIVE LOGITS

urance

1.15

ufficient

1.13

ights

1.12

iders

1.05

urg

0.97

ider

0.97

ert

0.95

urrection

0.95

idel

0.94

pection

0.93

Activations Density 0.007%

proper nouns or specific product names

the word "Ins" that likely indicates a specific topic or section in the document

No Comments

No Known Activations