INDEX

Explanations

instances of the word "ators" in various contexts

oai_token-act-pair · gpt-3.5-turbo

words related to roles or functions, particularly those ending in 'ator'

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

ASED

-0.84

LAN

-0.65

formed

-0.64

 Earth

-0.63

OUT

-0.63

PE

-0.62

CHAR

-0.62

MY

-0.62

Print

-0.62

Prof

-0.60

POSITIVE LOGITS

ators

1.32

hip

1.24

hips

1.01

atives

0.98

heses

0.92

":["

0.90

etter

0.89

paces

0.87

poons

0.87

culosis

0.87

Activations Density 0.013%

instances of the word "ators" in various contexts

words related to roles or functions, particularly those ending in 'ator'

No Comments

No Known Activations