INDEX

Explanations

words related to ascension or rising to power

oai_token-act-pair · gpt-3.5-turbo

terms related to ascension or elevation

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

 IMAGES

-0.73

bytes

-0.71

 Baird

-0.67

 Glock

-0.66

 Squid

-0.66

Goo

-0.66

meal

-0.66

 Grab

-0.65

 Franks

-0.65

Anderson

-0.64

POSITIVE LOGITS

ribed

1.19

ension

1.19

endant

1.18

 ascent

1.02

ribing

1.02

etics

0.94

 ascend

0.93

orns

0.93

ission

0.90

ribe

0.90

Activations Density 0.017%

words related to ascension or rising to power

terms related to ascension or elevation

No Comments

No Known Activations