INDEX

Explanations

phrases related to social organization and structure

oai_token-act-pair · gpt-3.5-turbo

concepts related to social justice and equality

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

latest

-0.94

inventoryQuantity

-0.79

UFC

-0.78

recent

-0.77

USS

-0.76

OUT

-0.75

URRENT

-0.74

VL

-0.72

Rare

-0.71

Used

-0.70

POSITIVE LOGITS

 inclusive

1.01

itarian

0.96

heid

0.94

 equality

0.92

ocracy

0.89

 democracy

0.89

clus

0.88

 equitable

0.87

opia

0.87

 egalitarian

0.86

Activations Density 0.532%

phrases related to social organization and structure

concepts related to social justice and equality

No Comments

No Known Activations