INDEX

Explanations

terms related to radiation in the context of disasters

oai_token-act-pair · gpt-3.5-turbo

references to radiation and its effects, specifically in relation to the Fukushima disaster

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

eenth

-0.85

theless

-0.75

neys

-0.75

lier

-0.74

lihood

-0.73

liness

-0.72

aws

-0.71

thood

-0.68

ernaut

-0.67

pages

-0.67

POSITIVE LOGITS

 radiation

1.16

 shielding

1.14

 irrad

1.10

 horm

1.07

 iodine

1.07

 detectors

1.03

 sickness

1.03

 isot

1.01

 doses

1.00

 emitted

1.00

Activations Density 0.042%

terms related to radiation in the context of disasters

references to radiation and its effects, specifically in relation to the Fukushima disaster

No Comments

No Known Activations