INDEX

Explanations

words related to natural disasters

oai_token-act-pair · gpt-3.5-turbo

terms related to disasters

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

eton

-0.83

ularity

-0.82

Ģ

-0.81

ells

-0.81

rab

-0.79

ular

-0.77

etition

-0.76

kaya

-0.75

erd

-0.74

eters

-0.73

POSITIVE LOGITS

 catast

1.04

ulence

0.89

 engulf

0.87

 disaster

0.84

 devast

0.83

 plag

0.82

 Disaster

0.81

 relief

0.79

 Katrina

0.78

 mitigation

0.78

Activations Density 0.024%

words related to natural disasters

terms related to disasters

No Comments

No Known Activations