INDEX

Explanations

references to specific institutions or places

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

ively

-0.78

iveness

-0.67

ailed

-0.66

uously

-0.59

è¦ļéĨĴ

-0.58

eeds

-0.57

||||

-0.56

 waiver

-0.55

utherford

-0.54

EF

-0.53

POSITIVE LOGITS

morph

0.84

ertodd

0.78

nom

0.70

oslav

0.67

©¶æ

0.66

anski

0.66

estone

0.64

graph

0.63

idon

0.63

shock

0.62

Activations Density 7.993%

references to specific institutions or places

No Comments

No Known Activations