INDEX

Explanations

words related to the city of Ottawa

oai_token-act-pair · gpt-3.5-turbo

mentions of the city Ottawa

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

ebook

-0.86

Ü

-0.77

ãĤ¦

-0.76

iles

-0.75

anmar

-0.73

âķĲâķĲ

-0.72

lihood

-0.70

-+-+

-0.68

âĵĺ

-0.68

eer

-0.67

POSITIVE LOGITS

apolis

1.05

 Senators

1.05

 Fury

0.94

sburgh

0.85

 Ottawa

0.81

awa

0.79

 Centre

0.74

ipeg

0.74

arians

0.73

boro

0.69

Activations Density 0.010%

words related to the city of Ottawa

mentions of the city Ottawa

No Comments

No Known Activations