INDEX

Explanations

information related to historical events, wars, military operations, and equipment

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reven

-0.72

RFC

-0.70

 Malays

-0.69

FORMATION

-0.67

MJ

-0.67

PDT

-0.64

 Torment

-0.64

ĸļ

-0.64

 Vega

-0.63

 vomiting

-0.63

POSITIVE LOGITS

pillar

1.26

apest

1.17

levard

1.13

lehem

1.09

hammad

1.04

ause

1.03

ĵĺ

1.02

aneers

1.00

reau

1.00

artisan

1.00

Activations Density 14.040%

information related to historical events, wars, military operations, and equipment

No Comments

No Known Activations