INDEX

Explanations

negative adjectives and phrases related to criticism and bias

oai_token-act-pair · gpt-3.5-turbo

terminology related to falsehoods and negative attributes in reports or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

cade

-0.84

ynthesis

-0.83

lear

-0.80

 Waves

-0.78

onds

-0.78

uese

-0.77

yles

-0.77

eatures

-0.77

ESE

-0.76

lights

-0.75

POSITIVE LOGITS

 disrespectful

1.43

 unethical

1.43

 immoral

1.41

 irresponsible

1.41

 wasteful

1.35

 prejud

1.34

 hypocritical

1.34

 counterproductive

1.33

 sexist

1.31

 racist

1.30

Activations Density 0.269%

negative adjectives and phrases related to criticism and bias

terminology related to falsehoods and negative attributes in reports or statements

No Comments

No Known Activations