INDEX

Explanations

names of cities, with a particular focus on Seattle

oai_token-act-pair · gpt-3.5-turbo

mentions of the city Seattle

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

ocr

-0.76

ktop

-0.73

arial

-0.72

Topic

-0.72

ï¿½ï¿½ï¿½ï¿½

-0.70

onies

-0.69

vit

-0.68

eline

-0.67

========

-0.66

ombs

-0.66

POSITIVE LOGITS

 Sounders

1.41

 Seahawks

1.21

 Mariners

1.21

 Tacoma

1.06

Seattle

1.02

ites

0.96

 Seattle

0.92

 Reign

0.89

 Seah

0.84

 Rapids

0.82

Activations Density 0.014%

names of cities, with a particular focus on Seattle

mentions of the city Seattle

No Comments

No Known Activations