INDEX

Explanations

words related to technical aspects like grids and energy systems

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

 Mehran

-0.81

/+

-0.73

ãģ¦

-0.72

iasis

-0.71

ermott

-0.69

lihood

-0.69

xual

-0.68

ivia

-0.67

ividual

-0.67

 Norn

-0.65

POSITIVE LOGITS

iron

1.24

lock

1.13

locked

1.08

 grid

1.04

 grids

0.94

mates

0.89

locking

0.80

 Grid

0.80

locks

0.79

lines

0.79

Activations Density 8.024%

words related to technical aspects like grids and energy systems

No Comments

No Known Activations