INDEX

Explanations

words related to challenging personal or social situations

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

 Lutheran

-0.66

overs

-0.64

uality

-0.62

Omn

-0.61

itutional

-0.61

notes

-0.60

ULT

-0.59

ORE

-0.58

idental

-0.58

alyst

-0.57

POSITIVE LOGITS

lette

0.78

rou

0.76

pton

0.72

pees

0.69

stan

0.66

 boun

0.64

plet

0.63

PDATE

0.63

ction

0.61

gged

0.61

Activations Density 6.544%

words related to challenging personal or social situations

No Comments

No Known Activations