INDEX

Explanations

instances where help or assistance is mentioned in various contexts or 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

Pict

-0.77

theless

-0.76

é¾

-0.76

ross

-0.73

ategory

-0.69

aval

-0.65

andom

-0.65

 Bellev

-0.65

 Viet

-0.64

guyen

-0.64

POSITIVE LOGITS

fully

1.04

des

0.89

 Desk

0.88

ful

0.79

enza

0.77

 broker

0.76

meet

0.75

full

0.75

aid

0.71

 remedy

0.70

Activations Density 7.459%

instances where help or assistance is mentioned in various contexts or situations

No Comments

No Known Activations