INDEX

Explanations

words related to law enforcement and criminal activity, such as names of drugs, police departments, illegal immigration, and law enforcement actions

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

 accur

-0.11

ortmund

-0.10

 arri

-0.10

alez

-0.10

 deprived

-0.10

¥µ

-0.10

 compr

-0.10

————

-0.10

 clutter

-0.10

 Kardash

-0.09

POSITIVE LOGITS

throp

0.18

peat

0.12

Jet

0.12

 Swordsman

0.11

emort

0.11

tails

0.11

abal

0.11

ortment

0.11

ect

0.10

tein

0.10

Activations Density 16.270%

words related to law enforcement and criminal activity, such as names of drugs, police departments, illegal immigration, and law enforcement actions

No Comments

No Known Activations

words related to law enforcement and criminal activity, such as names of drugs, police departments, illegal immigration, and law enforcement actions

No Comments

No Known Activations