INDEX

Explanations

references to the brand "Mercedes-Benz"

oai_token-act-pair · gpt-3.5-turbo

names of specific brands and notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

xon

-0.85

kees

-0.81

xia

-0.78

ffic

-0.77

uphem

-0.77

XT

-0.75

uberty

-0.72

lda

-0.71

peat

-0.70

ppo

-0.70

POSITIVE LOGITS

iere

0.80

iple

0.74

anca

0.70

ible

0.69

aker

0.68

ante

0.67

eners

0.66

inished

0.66

ened

0.66

auld

0.66

Activations Density 0.054%

references to the brand "Mercedes-Benz"

names of specific brands and notable individuals

No Comments

No Known Activations