INDEX

Explanations

phrases related to individuals being featured or participating as guests in various contexts

oai_token-act-pair · gpt-3.5-turbo

the word "guest."

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

resso

-0.75

nces

-0.73

remlin

-0.69

agically

-0.69

 Roche

-0.68

 Yard

-0.67

ancock

-0.67

okia

-0.67

hemat

-0.66

ochond

-0.65

POSITIVE LOGITS

 guest

1.11

Guest

1.04

 Guest

0.97

 guests

0.90

RTX

0.84

 accommodations

0.80

Doctor

0.77

 host

0.77

 accommodation

0.76

 hosts

0.76

Activations Density 0.007%

phrases related to individuals being featured or participating as guests in various contexts

the word "guest."

No Comments

No Known Activations