INDEX

Explanations

mentions of people's names or organizations with "pan" in it

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of individuals

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

glers

-1.06

FontSize

-0.69

LOAD

-0.68

#$#$

-0.65

INTON

-0.64

 Windsor

-0.64

Parameters

-0.64

GROUP

-0.64

Interested

-0.64

LET

-0.61

POSITIVE LOGITS

ossom

0.83

ieri

0.78

amic

0.75

ciating

0.74

xia

0.71

asy

0.70

ski

0.68

igham

0.68

ussen

0.67

chlor

0.65

Activations Density 0.497%

mentions of people's names or organizations with "pan" in it

proper nouns and names of individuals

No Comments

No Known Activations