INDEX

Explanations

names of individuals relating to academia and research

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

alam

-0.90

GROUND

-0.82

RECT

-0.79

cipline

-0.74

keeper

-0.73

arers

-0.73

unal

-0.73

taboola

-0.73

wark

-0.72

AKING

-0.72

POSITIVE LOGITS

imus

1.37

imil

1.31

imize

1.06

 Payne

1.02

imal

1.00

 Weber

0.97

itar

0.96

imen

0.94

imens

0.94

 Scher

0.91

Activations Density 7.580%

names of individuals relating to academia and research

No Comments

No Known Activations