INDEX

Explanations

references to radiators and related components in a mechanical or 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

lia

-0.59

laus

-0.59

liness

-0.58

lins

-0.57

spin

-0.56

lish

-0.56

ledged

-0.55

fully

-0.55

mint

-0.55

theless

-0.55

POSITIVE LOGITS

apers

0.58

otropic

0.57

orescence

0.57

ative

0.56

rogen

0.56

estate

0.54

ples

0.54

ologically

0.52

agen

0.52

aeda

0.52

Activations Density 6.977%

references to radiators and related components in a mechanical or technical context

No Comments

No Known Activations