INDEX

Explanations

general statements or facts related to people

oai_token-act-pair · gpt-3.5-turbo

references to the general perceptions or experiences of people

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ĪĴ

-0.75

 blackmail

-0.63

 unification

-0.61

 Lithuania

-0.61

hua

-0.60

 teammate

-0.60

enegger

-0.59

 uniqueness

-0.58

 destiny

-0.58

 timely

-0.57

POSITIVE LOGITS

 imaginable

0.95

 EVER

0.79

 except

0.77

Cent

0.72

ergic

0.71

 alike

0.70

immune

0.70

WER

0.69

dom

0.68

 revolves

0.68

Activations Density 0.202%

general statements or facts related to people

references to the general perceptions or experiences of people

No Known Activations