INDEX

Explanations

questions starting with "What is" followed by a specific topic

oai_token-act-pair · gpt-3.5-turbo

the phrase "What is" signaling inquiries or questions

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

hyde

-0.74

heres

-0.71

hedon

-0.69

lems

-0.67

 lash

-0.66

 Dickinson

-0.66

itches

-0.65

hens

-0.65

tails

-0.64

 sails

-0.64

POSITIVE LOGITS

omorphic

0.89

nt

0.87

 happening

0.85

 meant

0.77

 supposed

0.73

 actually

0.72

manship

0.67

 exactly

0.67

Ĥª

0.67

 ultimately

0.66

Activations Density 0.067%

questions starting with "What is" followed by a specific topic

the phrase "What is" signaling inquiries or questions

No Comments

No Known Activations