INDEX

Explanations

references to specific versions and implementations of programming languages

oai_token-act-pair · gpt-3.5-turbo

specific technical terms or acronyms related to software, programming, and technology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uyomi

-0.97

sburgh

-0.80

eous

-0.79

 Samoa

-0.77

 Tradable

-0.76

atchewan

-0.75

lihood

-0.74

olulu

-0.69

ãĥĩãĤ£

-0.68

owsky

-0.68

POSITIVE LOGITS

IM

1.17

PS

1.16

BC

1.10

BM

1.10

IC

1.05

EC

1.04

MC

1.03

OC

1.03

ML

1.02

FP

1.01

Activations Density 0.120%

references to specific versions and implementations of programming languages

specific technical terms or acronyms related to software, programming, and technology

No Comments

No Known Activations