INDEX

Explanations

mentions of a specific term "Durham"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Dur" or variations of it

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

 Simulator

-0.69

eries

-0.68

 directors

-0.67

ħĭ

-0.67

Lens

-0.64

NetMessage

-0.63

 Ethics

-0.61

esthetic

-0.61

tered

-0.59

 habitats

-0.58

POSITIVE LOGITS

ango

1.01

ably

0.99

anty

0.93

kan

0.92

andal

0.90

rell

0.89

antes

0.89

lock

0.88

abil

0.88

ability

0.88

Activations Density 0.025%

mentions of a specific term "Durham"

occurrences of the name "Dur" or variations of it

No Comments

No Known Activations