INDEX

Explanations

proper nouns or specific terms related to various industries and organizations

oai_token-act-pair · gpt-3.5-turbo

the end of document tokens

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

ĻĤ

-0.81

 notor

-0.78

 challeng

-0.77

arching

-0.75

etheless

-0.72

 tremend

-0.72

 autonom

-0.72

 toget

-0.71

 suspic

-0.71

 destro

-0.69

POSITIVE LOGITS

 Clause

1.07

 Room

1.06

 Desk

1.01

 Pieces

1.01

 Yards

1.00

 Guys

0.99

 Collection

0.99

 Score

0.98

 Productions

0.97

 Disorders

0.97

Activations Density 0.415%

proper nouns or specific terms related to various industries and organizations

the end of document tokens

No Comments

No Known Activations