INDEX

Explanations

words related to negative consequences or aftermath

oai_token-act-pair · gpt-3.5-turbo

references to "fallout" and its implications

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

licks

-0.81

cius

-0.81

ajo

-0.80

ced

-0.75

kie

-0.75

iverpool

-0.75

erved

-0.74

umbered

-0.73

essee

-0.73

kered

-0.72

POSITIVE LOGITS

 fallout

1.39

romeda

1.01

 spill

0.82

DragonMagazine

0.74

hower

0.71

 aftermath

0.70

 clouds

0.68

 crater

0.68

alore

0.67

 repercussions

0.67

Activations Density 0.012%

words related to negative consequences or aftermath

references to "fallout" and its implications

No Comments

No Known Activations