INDEX

Explanations

instances where questions are being answered

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the act of responding or providing answers to inquiries

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 marrow

-0.72

heric

-0.70

chin

-0.69

 Vengeance

-0.69

dar

-0.69

ombat

-0.69

ouf

-0.64

zinski

-0.64

cakes

-0.64

akin

-0.64

POSITIVE LOGITS

 questions

1.00

ysis

0.96

 Questions

0.89

answer

0.84

question

0.82

 honestly

0.78

 QUEST

0.78

 question

0.78

 answ

0.76

Question

0.76

Activations Density 0.028%

instances where questions are being answered

phrases indicating the act of responding or providing answers to inquiries

No Comments

No Known Activations