INDEX

Explanations

phrases related to early or immediate access or service

oai_token-act-pair · gpt-3.5-turbo

terms related to processes and roles in structured settings, particularly in advisory or analytical contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Books

-0.68

Vote

-0.65

ipes

-0.64

ushes

-0.64

pointers

-0.64

ombs

-0.63

istors

-0.63

 Faster

-0.62

lost

-0.62

 Congratulations

-0.61

POSITIVE LOGITS

 nature

1.57

 mode

1.50

 manner

1.50

 aspect

1.46

 basis

1.43

 format

1.40

 style

1.30

 guise

1.27

 fashion

1.27

 form

1.25

Activations Density 0.666%

phrases related to early or immediate access or service

terms related to processes and roles in structured settings, particularly in advisory or analytical contexts

No Comments

No Known Activations