INDEX

Explanations

phrases related to beginning or starting something

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the beginning of tasks or processes

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

orie

-0.75

jud

-0.70

ingly

-0.64

 bureau

-0.63

 Watergate

-0.63

bey

-0.62

 paed

-0.61

 judgement

-0.60

 wont

-0.60

 Bild

-0.57

POSITIVE LOGITS

ãĤ´

0.71

å§«

0.68

quist

0.67

igmatic

0.67

chedel

0.66

FIELD

0.65

geoning

0.65

 anew

0.65

 Credits

0.64

chy

0.63

Activations Density 0.030%

phrases related to beginning or starting something

phrases that indicate the beginning of tasks or processes

No Comments

No Known Activations