INDEX

Explanations

phrases indicating similarities or comparisons between different subjects

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or correlation, particularly involving the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

roy

-0.64

ISTER

-0.61

rend

-0.59

é¾įåĸļå£«

-0.58

 nonetheless

-0.57

 Mobility

-0.56

IQ

-0.56

GP

-0.56

oco

-0.56

SPONSORED

-0.55

POSITIVE LOGITS

ricanes

0.69

 usual

0.67

 outgoing

0.66

 predecessors

0.66

 plague

0.65

ettings

0.64

rats

0.63

 previous

0.63

ascript

0.63

ptions

0.62

Activations Density 0.185%

phrases indicating similarities or comparisons between different subjects

phrases that indicate causation or correlation, particularly involving the word "that."

No Comments

No Known Activations