INDEX

Explanations

the word "slate."

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "slate," particularly in contexts related to lists or upcoming events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abad

-0.77

alez

-0.76

ivation

-0.72

doms

-0.72

ivating

-0.67

ivated

-0.67

anooga

-0.67

oland

-0.67

thus

-0.67

rogens

-0.66

POSITIVE LOGITS

 slate

1.60

cloth

0.80

bilt

0.74

DAQ

0.74

wcsstore

0.73

 Pryor

0.70

cape

0.69

grass

0.68

mates

0.67

isode

0.67

Activations Density 0.009%

the word "slate."

mentions of the term "slate," particularly in contexts related to lists or upcoming events

No Comments

No Known Activations