INDEX

Explanations

words related to geographical locations, specific names, and terms related to legal processes and transactions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oup

-1.03

lihood

-1.03

CAR

-1.00

aturation

-1.00

holders

-0.97

ktop

-0.95

CRE

-0.95

Oy

-0.94

chool

-0.93

hr

-0.92

POSITIVE LOGITS

shaw

1.57

ming

1.55

senal

1.49

inals

1.46

inished

1.39

inally

1.36

é¾įåĸļå£«

1.29

ãĥ£

1.25

 Nadu

1.25

med

1.25

Activations Density 0.953%

words related to geographical locations, specific names, and terms related to legal processes and transactions

No Comments

No Known Activations