INDEX

Explanations

descriptions of physical actions and sequences of events happening in a narrative

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

rain

-1.02

ãĥķãĤ¡

-0.96

Times

-0.96

NULL

-0.95

gradation

-0.94

emo

-0.92

ifferent

-0.91

ict

-0.91

gress

-0.90

uci

-0.90

POSITIVE LOGITS

 consequently

1.80

 therefore

1.66

 hence

1.59

 thus

1.58

 then

1.57

 secondly

1.56

 thereby

1.50

 subsequently

1.33

 hopefully

1.32

 possibly

1.31

Activations Density 1.655%

descriptions of physical actions and sequences of events happening in a narrative

No Comments

No Known Activations