INDEX

Explanations

proper nouns and specific names related to various content creators or figures, potentially related to literature, gaming, or politics

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

etheless

-1.01

ãĥ¼ãĥĨãĤ£

-0.94

 numbered

-0.92

anwhile

-0.90

 Ajax

-0.84

ãĥ¼ãĥĨ

-0.83

ãģĨ

-0.82

 Leth

-0.80

OLOGY

-0.73

theless

-0.73

POSITIVE LOGITS

allow

1.39

attering

1.36

ooting

1.32

uffle

1.27

atters

1.27

uff

1.27

attered

1.27

aky

1.26

apesh

1.26

ackle

1.26

Activations Density 11.864%

proper nouns and specific names related to various content creators or figures, potentially related to literature, gaming, or politics

No Comments

No Known Activations