INDEX

Explanations

phrases related to life events or entities

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Life" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥĺ

-0.81

mented

-0.77

akedown

-0.75

Ń·

-0.74

MENTS

-0.73

sonian

-0.71

ractive

-0.70

uned

-0.68

agger

-0.67

 Cosponsors

-0.67

POSITIVE LOGITS

bringer

1.00

guards

0.93

guard

0.90

 expectancy

0.90

blood

0.83

mares

0.81

 Sciences

0.81

Site

0.80

 Matters

0.80

birth

0.78

Activations Density 0.016%

phrases related to life events or entities

mentions of the term "Life" in various contexts

No Comments

No Known Activations