INDEX

Explanations

terms related to metadata

oai_token-act-pair · gpt-3.5-turbo

content related to meta-analysis and related academic discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iens

-0.77

shire

-0.76

Interstitial

-0.76

 Franks

-0.74

 Vend

-0.72

ivity

-0.71

ESCO

-0.69

mingham

-0.68

HCR

-0.68

çİĭ

-0.66

POSITIVE LOGITS

plot

1.01

ethical

0.99

alyses

0.97

 guiActiveUn

0.86

allo

0.84

enter

0.82

ographically

0.78

verse

0.78

econom

0.77

hei

0.76

Activations Density 0.022%

terms related to metadata

content related to meta-analysis and related academic discussions

No Comments

No Known Activations