INDEX

Explanations

words related to specific entities, like names of organizations or places

oai_token-act-pair · gpt-3.5-turbo

names and terms related to specific organizations and cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pter

-0.82

pots

-0.81

vous

-0.79

*/(

-0.78

flies

-0.77

eyes

-0.77

 Dragonbound

-0.76

Accessory

-0.75

Boss

-0.74

assetsadobe

-0.74

POSITIVE LOGITS

 plur

0.89

ilater

0.72

 Afric

0.70

 Anth

0.70

Aus

0.69

 Assy

0.68

lation

0.68

 Palestin

0.67

avorite

0.66

uni

0.66

Activations Density 0.019%

words related to specific entities, like names of organizations or places

names and terms related to specific organizations and cultural references

No Comments

No Known Activations