INDEX

Explanations

phrases related to the well-being of individuals or groups

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

hyde

-0.90

ategory

-0.89

iferation

-0.84

ataka

-0.79

atto

-0.79

hip

-0.78

illary

-0.77

adena

-0.73

ription

-0.72

rush

-0.71

POSITIVE LOGITS

spring

1.24

enough

1.07

esley

1.04

 suited

0.96

ards

0.94

 behaved

0.93

 enough

0.89

reads

0.88

marked

0.88

planned

0.86

Activations Density 6.876%

phrases related to the well-being of individuals or groups

No Comments

No Known Activations