INDEX

Explanations

mathematical terms related to linearity

oai_token-act-pair · gpt-3.5-turbo

concepts and terms related to linear relationships and associated mathematical expressions

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

egu

-0.78

imester

-0.74

flies

-0.72

ardless

-0.70

aco

-0.67

ULTS

-0.66

IVERS

-0.66

illon

-0.65

IRED

-0.65

une

-0.65

POSITIVE LOGITS

linear

0.90

 algebra

0.88

ization

0.85

 interpol

0.85

 linear

0.81

gebra

0.80

gradient

0.80

 trajectory

0.78

 accelerator

0.77

izes

0.76

Activations Density 0.008%

mathematical terms related to linearity

concepts and terms related to linear relationships and associated mathematical expressions

No Comments

No Known Activations