INDEX

Explanations

words related to specific locations or cities

oai_token-act-pair · gpt-3.5-turbo

names of locations, particularly cities and regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

eal

-0.76

orter

-0.76

haar

-0.75

gerald

-0.73

ively

-0.73

ramid

-0.72

rained

-0.71

enegger

-0.69

sch

-0.69

win

-0.69

POSITIVE LOGITS

 Swansea

0.94

 City

0.90

 Cardiff

0.90

 Township

0.80

 Pictures

0.76

 Regener

0.74

 Tigers

0.72

 Yard

0.72

sburg

0.70

 University

0.70

Activations Density 0.004%

words related to specific locations or cities

names of locations, particularly cities and regions

No Comments

No Known Activations