INDEX

Explanations

phrases indicating emphasis or comparison

oai_token-act-pair · gpt-3.5-turbo

qualifying adjectives or adverbs emphasizing degree or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

è¦ļéĨĴ

-0.83

èĢ

-0.78

åĤ

-0.78

Ö

-0.77

ensis

-0.72

hett

-0.67

ãĥīãĥ©

-0.66

natureconservancy

-0.65

ãĤ¶

-0.65

opathy

-0.64

POSITIVE LOGITS

 Leader

0.84

resa

0.83

 Costs

0.82

 Ways

0.80

 Tracks

0.80

 Benefits

0.79

Of

0.77

 Enough

0.76

entimes

0.76

 Difference

0.76

Activations Density 0.146%

phrases indicating emphasis or comparison

qualifying adjectives or adverbs emphasizing degree or extent

No Comments

No Known Activations