INDEX

Explanations

technical terms related to data organization and analysis

oai_token-act-pair · gpt-3.5-turbo

terms related to organization and structure in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Origins

-0.63

 charism

-0.63

 Identity

-0.57

oÄŁ

-0.53

 Partnership

-0.51

Delivery

-0.51

 Liberation

-0.49

Status

-0.49

 Facts

-0.49

Population

-0.49

POSITIVE LOGITS

mith

1.29

pace

1.26

paces

1.26

hips

1.19

hip

1.17

peed

1.16

hift

1.11

heet

1.08

pring

1.08

creen

1.06

Activations Density 0.862%

technical terms related to data organization and analysis

terms related to organization and structure in various contexts

No Comments

No Known Activations