INDEX

Explanations

phrases indicating an action or decision being taken or made

oai_token-act-pair · gpt-3.5-turbo

phrases that include the term "pull out."

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

cius

-0.83

orld

-0.79

cious

-0.75

ingham

-0.74

shaw

-0.73

hedon

-0.73

vre

-0.72

orously

-0.71

ogun

-0.68

ioned

-0.67

POSITIVE LOGITS

stretched

0.97

 levers

0.82

wards

0.77

doors

0.72

 è£ıè

0.72

fitted

0.70

posts

0.67

WARD

0.64

 roots

0.63

casts

0.61

Activations Density 0.028%

phrases indicating an action or decision being taken or made

phrases that include the term "pull out."

No Comments

No Known Activations