INDEX

Explanations

words related to legal terms, specifically those related to assisted suicide laws

oai_token-act-pair · gpt-3.5-turbo

instances of the word "su" and its variations, indicating a focus on topics related to suicide

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

 Gutenberg

-0.77

neck

-0.69

Micro

-0.60

 Turks

-0.59

 louder

-0.58

 Schwe

-0.58

bug

-0.58

head

-0.57

anx

-0.56

 pain

-0.56

POSITIVE LOGITS

icide

1.33

arez

1.18

zanne

1.12

pper

1.08

perty

1.08

icides

1.07

perm

1.07

selage

1.01

icidal

0.99

ggle

0.92

Activations Density 0.025%

words related to legal terms, specifically those related to assisted suicide laws

instances of the word "su" and its variations, indicating a focus on topics related to suicide

No Comments

No Known Activations