INDEX

Explanations

various types of actions or concepts that are labeled or denoted by the term "calls"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating someone citing or referencing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

chant

-0.81

ysc

-0.80

earances

-0.72

ooter

-0.70

oult

-0.70

roleum

-0.69

umber

-0.67

eor

-0.67

inth

-0.66

psons

-0.66

POSITIVE LOGITS

0.78

0.73

Fra

0.67

 Quality

0.66

``

0.65

"(

0.63

"-

0.62

Fra

0.62

 "âĢ¦

0.62

BS

0.61

Activations Density 0.042%

various types of actions or concepts that are labeled or denoted by the term "calls"

phrases indicating someone citing or referencing something

No Comments

No Known Activations