INDEX

Explanations

names, particularly the last name "Poroshenko."

oai_token-act-pair · gpt-3.5-turbo

names of political figures and their associates

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

 newsp

-0.65

izont

-0.63

liest

-0.62

rike

-0.61

fuel

-0.60

 seeds

-0.59

Rev

-0.58

 welf

-0.58

itudinal

-0.57

 comprom

-0.56

POSITIVE LOGITS

zyk

0.88

igham

0.86

vous

0.84

enegger

0.80

obyl

0.77

icz

0.76

Äĩ

0.75

oglu

0.75

puff

0.74

enei

0.72

Activations Density 0.044%

names, particularly the last name "Poroshenko."

names of political figures and their associates

No Comments

No Known Activations