INDEX

Explanations

words or phrases that contain the letter 'E' followed by a number indicating the strength of the activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'E' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Cats

-0.67

ifications

-0.66

runners

-0.65

amaz

-0.64

eness

-0.64

ifier

-0.64

ifiable

-0.63

ification

-0.63

 Anthem

-0.60

ifiers

-0.60

POSITIVE LOGITS

fficient

1.21

instein

1.16

ASY

1.14

lements

1.13

LECT

1.06

cosystem

1.01

quality

1.00

FAULT

0.98

fficiency

0.96

ternity

0.96

Activations Density 0.045%

words or phrases that contain the letter 'E' followed by a number indicating the strength of the activation

occurrences of the letter 'E' in various contexts

No Comments

No Known Activations