INDEX

Explanations

numbers and rankings

oai_token-act-pair · gpt-3.5-turbo

rankings and positions of entities 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 @ 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

acet

-0.64

ç

-0.63

unity

-0.62

raid

-0.61

gery

-0.61

 Oath

-0.60

ollah

-0.59

idine

-0.58

 CONTIN

-0.57

 Lennon

-0.55

POSITIVE LOGITS

liest

0.93

 highest

0.88

 globally

0.87

ottest

0.86

highest

0.81

 overall

0.80

 Highest

0.80

orest

0.79

 trending

0.78

 worldwide

0.77

Activations Density 0.489%

numbers and rankings

rankings and positions of entities in various contexts

No Comments

No Known Activations