INDEX

Explanations

the word "expectations" in various contexts

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

ston

-0.67

stocks

-0.64

packing

-0.63

cise

-0.62

tan

-0.61

stab

-0.60

adan

-0.59

nan

-0.58

harm

-0.58

agra

-0.57

POSITIVE LOGITS

 expectations

0.86

 expectation

0.75

 Lauder

0.61

urity

0.60

 LEVEL

0.58

omething

0.57

 Ratio

0.56

 fulfil

0.56

 ceilings

0.56

LB

0.56

Activations Density 11.389%

the word "expectations" in various contexts

No Comments

No Known Activations