INDEX

Explanations

empty physical spaces

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "empty."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

abol

-0.83

arya

-0.78

dar

-0.75

ect

-0.73

CVE

-0.69

Downloadha

-0.68

ector

-0.68

 appropri

-0.67

NEWS

-0.66

Murray

-0.66

POSITIVE LOGITS

 space

0.83

igue

0.82

 empty

0.81

 Empty

0.80

 spaces

0.80

 calories

0.78

 shells

0.77

 bottles

0.76

empty

0.75

 slate

0.73

Activations Density 0.024%

empty physical spaces

occurrences of the word "empty."

No Comments

No Known Activations