INDEX

Explanations

mentions of the word "humanity"

oai_token-act-pair · gpt-3.5-turbo

mentions of humanity 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

raph

-0.70

urations

-0.69

 skim

-0.66

engers

-0.66

Bey

-0.65

abet

-0.64

FEC

-0.64

OHN

-0.63

INO

-0.61

 Rough

-0.61

POSITIVE LOGITS

ankind

1.00

 beings

0.95

zee

0.76

arily

0.74

zees

0.72

ÃŃs

0.72

itably

0.71

geist

0.70

 inhab

0.69

 flourishing

0.69

Activations Density 0.022%

mentions of the word "humanity"

mentions of humanity and its implications

No Comments

No Known Activations