INDEX

Explanations

phrases related to law enforcement incidents and investigations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffffcc

-1.00

theless

-0.91

Justice

-0.85

osure

-0.84

nerg

-0.83

 Written

-0.80

ï¸

-0.80

ãĤ

-0.80

ocaust

-0.78

cession

-0.77

POSITIVE LOGITS

 goodbye

1.22

IDA

0.85

olate

0.78

 they

0.77

it

0.74

icket

0.71

iaries

0.71

omething

0.71

ieu

0.70

paces

0.70

Activations Density 1.634%

phrases related to law enforcement incidents and investigations

No Comments

No Known Activations