INDEX

Explanations

terms related to timeframes and durations

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

riad

-0.75

ramid

-0.73

unin

-0.70

illard

-0.67

bold

-0.64

iasis

-0.61

artisan

-0.61

umar

-0.60

opoulos

-0.59

habi

-0.57

POSITIVE LOGITS

Duration

0.85

 periods

0.83

 duration

0.82

 elapsed

0.79

duration

0.78

interrupted

0.71

 expires

0.70

 leng

0.69

 lapse

0.68

 period

0.67

Activations Density 9.109%

terms related to timeframes and durations

No Comments

No Known Activations