INDEX

Explanations

phrases related to personal experiences and stories, including reflections, anecdotes, and personal opinions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Became

-0.74

iencies

-0.71

orks

-0.70

Ago

-0.69

hips

-0.67

renches

-0.66

storms

-0.65

reys

-0.64

css

-0.64

doms

-0.64

POSITIVE LOGITS

 favourite

1.29

 favorite

1.28

own

1.21

 biggest

1.09

 favorites

1.08

 consolation

1.08

 strongest

1.06

 preferred

1.03

 rightful

1.03

 choice

1.02

Activations Density 9.456%

phrases related to personal experiences and stories, including reflections, anecdotes, and personal opinions

No Comments

No Known Activations