INDEX

Explanations

news-related terms and references

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

 veter

-0.89

heat

-0.84

acea

-0.75

Initialized

-0.73

ËĪ

-0.72

OPA

-0.72

english

-0.71

mpire

-0.69

gex

-0.69

[_

-0.68

POSITIVE LOGITS

 underscores

0.79

 announcement

0.75

 illustrates

0.71

 spree

0.70

 coincided

0.69

 coincides

0.69

 represents

0.69

 Kron

0.69

 includes

0.68

 deadline

0.68

Activations Density 2.243%

news-related terms and references

No Comments

No Known Activations