INDEX

Explanations

commands or instructions in a technical context

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

±

-0.74

¶æ

-0.73

aukee

-0.67

)</

-0.67

DERR

-0.66

gger

-0.61

gran

-0.60

¨

-0.58

sbm

-0.58

unin

-0.58

POSITIVE LOGITS

:-

0.77

:(

0.77

":[

0.68

 assumes

0.67

0.66

 configure

0.65

 demonstrates

0.62

>:

0.61

 illustrates

0.61

:'

0.61

Activations Density 9.824%

commands or instructions in a technical context

No Comments

No Known Activations