INDEX

Explanations

answers or responses in the context of various scenarios

oai_token-act-pair · gpt-3.5-turbo

phrases related to responding or providing answers to questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

erker

-0.81

heric

-0.79

ammy

-0.77

enic

-0.76

ovie

-0.76

 Nanto

-0.72

chin

-0.72

esm

-0.71

zinski

-0.71

enburg

-0.69

POSITIVE LOGITS

 answ

1.10

answer

1.00

swers

0.99

 answering

0.98

Answer

0.98

 answered

0.98

ysis

0.97

 answer

0.96

 Answer

0.88

 Questions

0.83

Activations Density 0.021%

answers or responses in the context of various scenarios

phrases related to responding or providing answers to questions

No Comments

No Known Activations