INDEX

Explanations

company names and related terms

oai_token-act-pair · gpt-3.5-turbo

names of individuals or brands related to technology and media

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

-0.73

 "$:/

-0.73

::::::::

-0.69

():

-0.62

—-

-0.62

————————

-0.61

soever

-0.60

emen

-0.60

 âĢº

-0.58

——

-0.58

POSITIVE LOGITS

 Moroc

0.81

etheless

0.80

senal

0.76

hovah

0.73

yang

0.73

sterdam

0.72

srf

0.69

ĪĴ

0.69

ween

0.69

ĸļå£«

0.65

Activations Density 0.658%

company names and related terms

names of individuals or brands related to technology and media

No Comments

No Known Activations