INDEX

Explanations

phrases related to technical instructions or programming commands

oai_token-act-pair · gpt-3.5-turbo

prepositions and their usage 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

arak

-0.72

omsky

-0.69

zzy

-0.64

isa

-0.63

ento

-0.61

uti

-0.61

styles

-0.59

innie

-0.57

IRO

-0.57

wine

-0.56

POSITIVE LOGITS

 itself

1.00

its

0.90

 himself

0.81

 oneself

0.73

 herself

0.73

ITS

0.71

pload

0.70

 ourselves

0.70

rer

0.64

his

0.64

Activations Density 0.414%

phrases related to technical instructions or programming commands

prepositions and their usage in various contexts

No Comments

No Known Activations