INDEX

Explanations

words related to danger and risk

oai_token-act-pair · gpt-3.5-turbo

instances of the term "dangerous."

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

via

-0.85

arist

-0.81

ļéĨĴ

-0.79

mination

-0.77

roma

-0.76

olitan

-0.76

anish

-0.76

á

-0.75

elf

-0.75

angular

-0.74

POSITIVE LOGITS

 undermin

0.92

 adolesc

0.90

 dangerous

0.88

 endanger

0.88

 danger

0.81

danger

0.80

 sounding

0.77

 dangers

0.76

 mischief

0.76

 Danger

0.74

Activations Density 0.019%

words related to danger and risk

instances of the term "dangerous."

No Comments

No Known Activations