INDEX

Explanations

detailed descriptions or stories, likely from news articles or reviews

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

ãĥ¼ãĥĨ

-0.77

rency

-0.69

 lean

-0.69

 Cosponsors

-0.67

hement

-0.67

 GOODMAN

-0.64

ãĤ¨ãĥ«

-0.63

staking

-0.63

furt

-0.63

 redes

-0.63

POSITIVE LOGITS

ovych

0.82

horn

0.72

ÅĤ

0.70

cock

0.67

ws

0.67

scl

0.67

################

0.67

ulic

0.65

 Picture

0.65

velop

0.65

Activations Density 24.004%

detailed descriptions or stories, likely from news articles or reviews

No Comments

No Known Activations