INDEX

Explanations

references to sports teams and player statistics

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

izoph

-0.60

 disemb

-0.58

!--

-0.58

 perspect

-0.58

 mascul

-0.56

 humour

-0.56

 arte

-0.55

 feminine

-0.55

 silence

-0.55

 flora

-0.54

POSITIVE LOGITS

 Granted

0.80

 Conversely

0.79

 Needless

0.77

 Additionally

0.74

 Consequently

0.72

 However

0.71

 Unfortunately

0.71

 Furthermore

0.71

 Afterwards

0.71

 Considering

0.71

Activations Density 3.445%

references to sports teams and player statistics

No Comments

No Known Activations