INDEX

Explanations

words related to physical objects or equipment

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

 Finance

-0.60

 finance

-0.58

Laun

-0.57

apers

-0.55

 Andromeda

-0.54

 Dangerous

-0.54

Birth

-0.53

 Health

-0.53

 Colleges

-0.51

 Streets

-0.51

POSITIVE LOGITS

asus

0.66

variable

0.65

 bonded

0.64

luster

0.60

zyme

0.60

 inhibitor

0.60

pointer

0.59

icone

0.59

 attached

0.58

iple

0.57

Activations Density 17.551%

words related to physical objects or equipment

No Comments

No Known Activations