INDEX

Explanations

mentions of specific names, particularly of individuals associated with specific events or organizations

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

âĸ¬âĸ¬

-1.08

EMENT

-1.08

IBLE

-1.02

âķĲâķĲ

-1.00

éĹĺ

-0.99

 FANTASY

-0.99

LECT

-0.98

MENT

-0.93

BALL

-0.92

FOX

-0.91

POSITIVE LOGITS

aji

1.53

orne

1.35

osh

1.24

orns

1.20

arna

1.20

oul

1.18

alid

1.17

azard

1.16

ahah

1.16

ush

1.16

Activations Density 1.073%

mentions of specific names, particularly of individuals associated with specific events or organizations

No Comments

No Known Activations