INDEX

Explanations

surnames or names of people

oai_token-act-pair · gpt-3.5-turbo

words related to names or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

udeb

-0.80

mble

-0.79

ebted

-0.75

ugi

-0.70

SpaceEngineers

-0.69

Magikarp

-0.65

ymph

-0.65

Ô

-0.65

¾

-0.63

vg

-0.62

POSITIVE LOGITS

mania

0.80

hower

0.80

 County

0.78

ville

0.72

 Grove

0.72

 Sachs

0.72

 Highlights

0.69

 agrees

0.69

 acknowledges

0.68

sonian

0.67

Activations Density 0.244%

surnames or names of people

words related to names or places

No Comments

No Known Activations