INDEX

Explanations

language signaling an explanation, analysis, or comparison

oai_token-act-pair · gpt-3.5-turbo

instances and contexts of conditional situations or cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

itialized

-0.80

 QUEST

-0.70

 Nurs

-0.65

ĪĴ

-0.60

guyen

-0.58

PET

-0.57

irs

-0.56

lav

-0.56

 RAID

-0.55

uador

-0.55

POSITIVE LOGITS

ãĢĤ

0.90

0.81

.[

0.78

.</

0.77

.",

0.77

.ï¿½

0.74

.*

0.70

.''

0.70

 outwe

0.68

.","

0.68

Activations Density 0.369%

language signaling an explanation, analysis, or comparison

instances and contexts of conditional situations or cases

No Comments

No Known Activations