INDEX

Explanations

details related to individual stories or events within a larger context, like sports matches or personal experiences

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otic

-0.70

arta

-0.69

ians

-0.62

mare

-0.61

asm

-0.55

ethy

-0.55

obi

-0.54

inas

-0.54

oto

-0.54

otes

-0.53

POSITIVE LOGITS

 reluct

0.64

 originally

0.64

 teasp

0.62

 uproar

0.61

 pandemonium

0.60

 murm

0.60

 initially

0.60

 instrumental

0.60

MpServer

0.60

wolves

0.60

Activations Density 10.799%

details related to individual stories or events within a larger context, like sports matches or personal experiences

No Comments

No Known Activations