INDEX

Explanations

instructions or steps related to software or code implementation

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

 Bridgewater

-0.60

 Victims

-0.52

Prosecut

-0.52

 Mutual

-0.51

 Constantin

-0.51

mma

-0.50

cas

-0.49

egal

-0.49

 debtor

-0.48

venge

-0.48

POSITIVE LOGITS

 swipe

0.70

 CTRL

0.65

 inputs

0.64

chairs

0.63

 cursor

0.61

 buttons

0.60

ername

0.59

trl

0.58

abel

0.58

 gestures

0.56

Activations Density 7.646%

instructions or steps related to software or code implementation

No Comments

No Known Activations