INDEX

Explanations

expressions related to debt or obligation

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

markets

-0.79

 Expand

-0.78

nel

-0.78

cross

-0.77

nets

-0.75

unch

-0.74

aque

-0.72

alist

-0.72

ocol

-0.72

dq

-0.71

POSITIVE LOGITS

 allegiance

1.00

 owed

0.93

 forgiveness

0.92

 repayment

0.89

Credit

0.83

 forgiven

0.81

ODUCT

0.81

gers

0.81

 repay

0.78

 dearly

0.78

Activations Density 10.372%

expressions related to debt or obligation

No Comments

No Known Activations