INDEX

Explanations

specific county names

oai_token-act-pair · gpt-3.5-turbo

references to county designations in a legal or news context

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

furt

-0.88

Ö¼

-0.82

aeus

-0.82

isks

-0.80

ãĥĦ

-0.79

toc

-0.78

bub

-0.77

ylan

-0.76

ipedia

-0.76

otten

-0.75

POSITIVE LOGITS

 Sheriff

1.21

 sheriff

1.10

 District

1.05

 County

1.05

 Jail

1.03

 commissioners

1.00

 Commissioners

1.00

wide

0.99

 Correctional

0.97

 Supervisor

0.97

Activations Density 0.031%

specific county names

references to county designations in a legal or news context

No Comments

No Known Activations