INDEX

Explanations

mentions of people's names

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

 margins

-0.80

llor

-0.79

CLASSIFIED

-0.73

 minded

-0.68

¥ŀ

-0.68

eering

-0.65

 lone

-0.65

GoldMagikarp

-0.65

 conspicuous

-0.65

 actionGroup

-0.64

POSITIVE LOGITS

zig

1.17

forth

1.09

ube

0.96

emark

0.93

alog

0.92

olver

0.92

ilo

0.92

coni

0.92

vier

0.90

 Marino

0.90

Activations Density 5.460%

mentions of people's names

No Comments

No Known Activations