INDEX

Explanations

terms related to visibility or prominence

oai_token-act-pair · gpt-3.5-turbo

terminologies related to notable figures and cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dome

-0.80

fax

-0.77

WARD

-0.68

 Shack

-0.67

Jed

-0.65

 ..............

-0.64

Kick

-0.63

yll

-0.62

bye

-0.61

Hill

-0.61

POSITIVE LOGITS

ance

1.16

atory

1.10

aries

1.06

osity

1.03

ations

1.02

ational

1.00

ances

0.98

ancy

0.97

istics

0.96

ancies

0.93

Activations Density 0.044%

terms related to visibility or prominence

terminologies related to notable figures and cultural references

No Comments

No Known Activations