INDEX

Explanations

phrases related to naming or describing things

oai_token-act-pair · gpt-3.5-turbo

statements that attribute specific actions or characteristics to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aver

-0.72

icles

-0.68

entity

-0.66

azon

-0.63

airo

-0.62

 withd

-0.62

 confir

-0.61

izards

-0.61

oids

-0.61

ants

-0.60

POSITIVE LOGITS

an

0.82

0.79

 insur

0.78

 constructive

0.73

 blatant

0.72

 unfair

0.70

 rudimentary

0.67

erous

0.67

 Byzantine

0.67

 frivolous

0.66

Activations Density 0.079%

phrases related to naming or describing things

statements that attribute specific actions or characteristics to individuals or entities

No Comments

No Known Activations