INDEX

Explanations

questions or statements contemplating possibilities or outcomes

oai_token-act-pair · gpt-3.5-turbo

questions beginning with "how," "what," or "why."

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

catentry

-0.97

arget

-0.75

rawdownloadcloneembedreportprint

-0.72

MpServer

-0.71

alde

-0.71

alysed

-0.69

FN

-0.69

iege

-0.69

assad

-0.68

POSITIVE LOGITS

 motives

0.75

 pige

0.75

why

0.75

 forgiveness

0.71

WHY

0.69

 coincidence

0.69

 retribution

0.67

 sincerity

0.67

 nostalg

0.67

 distingu

0.66

Activations Density 0.097%

questions or statements contemplating possibilities or outcomes

questions beginning with "how," "what," or "why."

No Comments

No Known Activations