INDEX

Explanations

words related to interactive elements or actions

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to toggling and the Snapchat application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ural

-0.80

ures

-0.77

esses

-0.76

raid

-0.75

ess

-0.74

ivist

-0.72

idi

-0.72

icket

-0.71

ament

-0.71

resses

-0.69

POSITIVE LOGITS

DERR

0.71

APE

0.69

 Apprentice

0.67

rection

0.66

âĶĢ

0.65

Drag

0.64

@@@@@@@@

0.63

CENT

0.63

————

0.62

aneous

0.62

Activations Density 0.071%

words related to interactive elements or actions

terms and concepts related to toggling and the Snapchat application

No Comments

No Known Activations