INDEX

Explanations

phrases related to metropolitan areas

oai_token-act-pair · gpt-3.5-turbo

references to metropolitan areas

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

arin

-0.86

nir

-0.83

vous

-0.80

roma

-0.80

uth

-0.75

yer

-0.74

enes

-0.74

itars

-0.72

etheus

-0.72

*/(

-0.71

POSITIVE LOGITS

 metropolitan

1.21

 area

0.85

 tracts

0.83

 dwell

0.81

 areas

0.80

ãĥ³ãĤ¸

0.77

 skyline

0.77

 illiter

0.77

 regions

0.76

oun

0.74

Activations Density 0.008%

phrases related to metropolitan areas

references to metropolitan areas

No Comments

No Known Activations