INDEX

Explanations

different categories or types of items or entities

oai_token-act-pair · gpt-3.5-turbo

lists and enumerations of items or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

swick

-0.88

xus

-0.76

afia

-0.75

ucker

-0.74

ippi

-0.74

ueller

-0.74

ilege

-0.71

akis

-0.69

atsu

-0.69

atican

-0.69

POSITIVE LOGITS

 unpop

0.76

rogens

0.72

 meaning

0.67

 agile

0.67

 durable

0.66

 Manufacturer

0.66

adj

0.65

 albeit

0.65

 clothed

0.64

meaning

0.64

Activations Density 0.434%

different categories or types of items or entities

lists and enumerations of items or categories

No Comments

No Known Activations