INDEX

Explanations

instances of the word "Rondo" in the content

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

creen

-0.65

sis

-0.64

wagen

-0.64

rooms

-0.62

sburg

-0.61

orescent

-0.58

ardless

-0.58

roots

-0.58

itates

-0.58

metics

-0.57

POSITIVE LOGITS

agate

0.68

 Alonso

0.62

ragon

0.60

ando

0.59

zzle

0.59

emonium

0.57

qua

0.56

jo

0.54

Sop

0.53

Gig

0.53

Activations Density 9.736%

instances of the word "Rondo" in the content

No Comments

No Known Activations