INDEX

Explanations

descriptions related to reproductive behavior in animals

oai_token-act-pair · gpt-3.5-turbo

terminology related to gender, reproduction, and life stages in animals

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

Negative Logits

Ń·

-1.08

leans

-0.96

uyomi

-0.88

£ı

-0.84

 lawy

-0.81

Crime

-0.80

orney

-0.80

ihadi

-0.75

ĪĴ

-0.75

å¥³

-0.74

POSITIVE LOGITS

 hatch

0.92

 mate

0.87

lings

0.85

sow

0.83

 specimens

0.83

 mating

0.82

 Eggs

0.81

 hatched

0.81

Egg

0.80

 Gibbs

0.80

Activations Density 0.109%

descriptions related to reproductive behavior in animals

terminology related to gender, reproduction, and life stages in animals

No Known Activations