INDEX

Explanations

acronyms related to organizations

oai_token-act-pair · gpt-3.5-turbo

references to a specific communication technology or concept

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.71

 è£ıè¦ļéĨĴ

-0.70

lihood

-0.69

 Carmen

-0.66

Dru

-0.66

Magikarp

-0.65

bilt

-0.64

strument

-0.64

 Cyrus

-0.62

tenance

-0.62

POSITIVE LOGITS

asting

0.90

ruits

0.86

urrent

0.86

ritical

0.83

ords

0.82

urry

0.81

ORE

0.81

ombo

0.79

actions

0.79

emetery

0.79

Activations Density 0.011%

acronyms related to organizations

references to a specific communication technology or concept

No Comments

No Known Activations