INDEX

Explanations

names of people and locations

oai_token-act-pair · gpt-3.5-turbo

occurrences and variations of the word "of"

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

attribute

-0.80

 disag

-0.78

kered

-0.76

parency

-0.74

*.

-0.72

TEXT

-0.69

ioned

-0.68

 surrog

-0.64

âĨĳ

-0.63

 void

-0.62

POSITIVE LOGITS

 Pasadena

0.81

 Auckland

0.80

 Sicily

0.76

Ward

0.75

 whom

0.74

 Queens

0.74

 Rochester

0.74

 Emer

0.74

Elm

0.73

 Antioch

0.73

Activations Density 0.089%

names of people and locations

occurrences and variations of the word "of"

No Comments

No Known Activations