INDEX

Explanations

words related to individuals with "Jr" as part of their name

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "Jr." in reference to 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

=-=-=-=-=-=-=-=-

-0.75

Cover

-0.72

keeping

-0.69

 è£ıç

-0.67

Front

-0.66

 Petraeus

-0.65

 Marketable

-0.65

point

-0.64

lords

-0.63

lled

-0.63

POSITIVE LOGITS

onse

0.99

Jr

0.96

.,

0.91

igne

0.87

quez

0.84

usalem

0.83

uez

0.82

arcer

0.82

Sr

0.82

inx

0.79

Activations Density 0.015%

words related to individuals with "Jr" as part of their name

occurrences of the abbreviation "Jr." in reference to individuals

No Comments

No Known Activations