INDEX

Explanations

mentions of the city Jerusalem

oai_token-act-pair · gpt-3.5-turbo

references to the city of Jerusalem

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ramid

-0.81

BOOK

-0.81

lass

-0.77

istration

-0.77

ured

-0.74

lasses

-0.74

ority

-0.73

uration

-0.72

ktop

-0.71

raviolet

-0.70

POSITIVE LOGITS

usalem

1.14

 Jerusalem

1.12

 Pradesh

0.82

 Galile

0.79

 Township

0.77

 Aviv

0.76

 Municip

0.75

 Heights

0.75

 correspondent

0.71

ites

0.71

Activations Density 0.007%

mentions of the city Jerusalem

references to the city of Jerusalem

No Comments

No Known Activations