INDEX

Explanations

keywords related to politics and governance

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

ixel

-0.74

noon

-0.71

PK

-0.70

:(

-0.69

rb

-0.69

Beg

-0.68

poke

-0.67

ESH

-0.66

._

-0.65

omics

-0.63

POSITIVE LOGITS

etc

1.14

etc

1.14

 assorted

1.08

 others

0.84

 other

0.77

whatever

0.75

ĪĴ

0.74

 possibly

0.73

 kindred

0.67

ect

0.67

Activations Density 18.466%

keywords related to politics and governance

No Comments

No Known Activations