INDEX

Explanations

words related to rules, regulations, consequences, and penalties

oai_token-act-pair · gpt-3.5-turbo

concepts related to societal rules, norms, and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

iven

-0.67

ãĥĳ

-0.65

ãĥķãĤ©

-0.63

ophon

-0.62

ãĤ»

-0.61

ando

-0.60

 Siber

-0.59

ãĥĭ

-0.59

SPONSORED

-0.59

`.

-0.59

POSITIVE LOGITS

 deserve

0.98

 tended

0.96

 will

0.91

 must

0.89

are

0.87

 cannot

0.86

may

0.86

 ought

0.85

 knows

0.84

 tend

0.84

Activations Density 0.676%

words related to rules, regulations, consequences, and penalties

concepts related to societal rules, norms, and consequences

No Comments

No Known Activations