INDEX

Explanations

instances where something is visible or can be seen

oai_token-act-pair · gpt-3.5-turbo

words related to visibility and the concept of being seen

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

inion

-0.81

allo

-0.81

upuncture

-0.79

artment

-0.77

acci

-0.73

auri

-0.72

req

-0.71

ilit

-0.71

axter

-0.70

stead

-0.69

POSITIVE LOGITS

 signs

0.91

 visible

0.81

 Signs

0.79

seeing

0.76

 silhou

0.75

isable

0.71

 billboards

0.71

 markers

0.70

ible

0.69

 silhouette

0.68

Activations Density 0.046%

instances where something is visible or can be seen

words related to visibility and the concept of being seen

No Comments

No Known Activations