INDEX

Explanations

phrases or terms related to specific locations or entities such as "Nos" and "Wyn."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Nos" or variations of it, which may indicate a focus on a specific entity or concept

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vantage

-0.80

riel

-0.75

assies

-0.75

onomous

-0.70

owered

-0.68

 Archdemon

-0.67

regn

-0.65

qua

-0.64

------------

-0.63

board

-0.63

POSITIVE LOGITS

uits

0.85

teenth

0.83

cha

0.81

creen

0.80

adequ

0.76

uit

0.75

umbers

0.74

cale

0.74

ieth

0.71

ppo

0.71

Activations Density 0.024%

phrases or terms related to specific locations or entities such as "Nos" and "Wyn."

mentions of the name "Nos" or variations of it, which may indicate a focus on a specific entity or concept

No Comments

No Known Activations