INDEX

Explanations

references to specific levels or conditions of something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "its" as well as variations of possession

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

 Bucc

-0.72

 Vikings

-0.69

 Republicans

-0.66

 Coup

-0.66

 Saudis

-0.64

 Indians

-0.64

 Democrats

-0.63

Cf

-0.62

 Sear

-0.62

 Blacks

-0.62

POSITIVE LOGITS

own

1.13

 stride

0.96

 infancy

0.93

 entirety

0.81

 heels

0.78

 rightful

0.78

 adolesc

0.78

 millenn

0.77

 knees

0.77

ailability

0.75

Activations Density 0.170%

references to specific levels or conditions of something

occurrences of the word "its" as well as variations of possession

No Comments

No Known Activations