INDEX

Explanations

references to individuals, particularly those in positions of authority or influence

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

names of different people

oai_token-act-pair · gpt-3.5-turbo

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

essional

-0.72

DAQ

-0.69

hops

-0.69

âĸĵ

-0.66

ISTORY

-0.65

ãĥīãĥ©

-0.65

uzz

-0.62

FORMATION

-0.62

Ñĭ

-0.60

bob

-0.60

POSITIVE LOGITS

ongyang

0.81

pai

0.80

artisan

0.80

enei

0.78

 Plat

0.77

 Stras

0.76

 Kant

0.75

ilon

0.74

lett

0.74

sonian

0.73

Activations Density 0.038%

references to individuals, particularly those in positions of authority or influence

names of different people

No Comments

No Known Activations