INDEX

Explanations

numbers that appear to have significance or importance

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

awaru

-0.73

arial

-0.64

iguous

-0.63

ilic

-0.62

icularly

-0.62

romeda

-0.62

riel

-0.61

ificial

-0.60

rolet

-0.60

opping

-0.60

POSITIVE LOGITS

Ħ¢

0.68

tm

0.68

%,

0.67

XL

0.66

+,

0.65

ÃĹ

0.65

nd

0.65

Â½

0.64

rd

0.63

 Intermediate

0.60

Activations Density 12.699%

numbers that appear to have significance or importance

No Comments

No Known Activations