INDEX

Explanations

references to terms starting with 'ther'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ther" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ELS

-0.85

URI

-0.78

 Chao

-0.68

 Pilgrim

-0.67

 Peel

-0.66

 retrospective

-0.63

 Dele

-0.63

 OECD

-0.63

Pu

-0.61

 admirable

-0.61

POSITIVE LOGITS

apy

1.37

ther

1.14

idge

1.14

apist

1.06

swer

1.04

pher

0.98

netic

0.96

dinand

0.95

mal

0.93

rha

0.92

Activations Density 0.004%

references to terms starting with 'ther'

occurrences of the substring "ther" in various contexts

No Comments

No Known Activations