INDEX

Explanations

dates and time descriptions

oai_token-act-pair · gpt-3.5-turbo

numerical ratings and symbols related to scoring or evaluations

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

KI

-0.78

pell

-0.70

Reloaded

-0.68

leep

-0.67

MN

-0.66

heed

-0.66

enza

-0.64

oko

-0.62

pread

-0.62

BW

-0.62

POSITIVE LOGITS

 Vulkan

0.87

 Dalai

0.70

RTX

0.65

 Anniversary

0.65

\-

0.64

 Duration

0.63

 Mastery

0.61

 âĢİ

0.61

 Prest

0.61

 Completed

0.60

Activations Density 0.025%

dates and time descriptions

numerical ratings and symbols related to scoring or evaluations

No Comments

No Known Activations